1

Child-Emotion-Code

@@ -1 +0,0 @@
-Subproject commit 48d9fdda49f14336ee9bd109ea3b952ff216cf41

audio_model_states/fastspeech2_canton_onnx_1.4.0/fastspeech2_canton.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4e164f9290eb7f4a696568b8209ffc0435c9d3721ec276ae4d72e8e9f90f65
+size 150460283

audio_model_states/fastspeech2_canton_onnx_1.4.0/phone_id_map.txt

@@ -0,0 +1,289 @@
+<pad> 0
+<unk> 1
+1 2
+2 3
+3 4
+4 5
+5 6
+6 7
+a 8
+a1 9
+a3 10
+aa 11
+aa1 12
+aa2 13
+aa3 14
+aa4 15
+aa5 16
+aa6 17
+aai1 18
+aai2 19
+aai3 20
+aai4 21
+aai5 22
+aai6 23
+aak1 24
+aak3 25
+aak6 26
+aam1 27
+aam2 28
+aam3 29
+aam4 30
+aam5 31
+aam6 32
+aan1 33
+aan2 34
+aan3 35
+aan4 36
+aan5 37
+aan6 38
+aang1 39
+aang2 40
+aang4 41
+aang5 42
+aang6 43
+aap3 44
+aap6 45
+aat1 46
+aat3 47
+aat6 48
+aau1 49
+aau2 50
+aau3 51
+aau4 52
+aau5 53
+aau6 54
+ai 55
+ai1 56
+ai2 57
+ai3 58
+ai4 59
+ai5 60
+ai6 61
+ak 62
+ak1 63
+ak6 64
+am1 65
+am2 66
+am3 67
+am4 68
+am5 69
+am6 70
+an1 71
+an2 72
+an3 73
+an4 74
+an5 75
+an6 76
+ang1 77
+ang2 78
+ang3 79
+ang4 80
+ang6 81
+ap1 82
+ap6 83
+at1 84
+at2 85
+at6 86
+au 87
+au1 88
+au2 89
+au3 90
+au4 91
+au5 92
+au6 93
+b 94
+c 95
+d 96
+e 97
+e1 98
+e2 99
+e3 100
+e4 101
+e5 102
+e6 103
+ei1 104
+ei2 105
+ei3 106
+ei4 107
+ei5 108
+ei6 109
+ek1 110
+ek3 111
+ek6 112
+eng1 113
+eng2 114
+eng3 115
+eng4 116
+eng5 117
+eng6 118
+eoi1 119
+eoi2 120
+eoi3 121
+eoi4 122
+eoi5 123
+eoi6 124
+eon1 125
+eon2 126
+eon3 127
+eon4 128
+eon5 129
+eon6 130
+eot1 131
+eot6 132
+f 133
+g 134
+gw 135
+h 136
+i1 137
+i2 138
+i3 139
+i4 140
+i5 141
+i6 142
+ik1 143
+ik6 144
+im1 145
+im2 146
+im3 147
+im4 148
+im5 149
+im6 150
+in1 151
+in2 152
+in3 153
+in4 154
+in5 155
+in6 156
+ing1 157
+ing2 158
+ing3 159
+ing4 160
+ing5 161
+ing6 162
+ip3 163
+ip6 164
+it1 165
+it3 166
+it6 167
+iu1 168
+iu2 169
+iu3 170
+iu4 171
+iu5 172
+iu6 173
+j 174
+k 175
+k1 176
+kw 177
+l 178
+m 179
+m1 180
+m3 181
+n 182
+n3 183
+ng 184
+o 185
+o1 186
+o2 187
+o3 188
+o4 189
+o5 190
+o6 191
+oe1 192
+oek2 193
+oek3 194
+oek6 195
+oeng1 196
+oeng2 197
+oeng3 198
+oeng4 199
+oeng5 200
+oeng6 201
+oi 202
+oi1 203
+oi2 204
+oi3 205
+oi4 206
+oi6 207
+ok 208
+ok1 209
+ok2 210
+ok3 211
+ok6 212
+on 213
+on1 214
+on2 215
+on3 216
+on4 217
+on6 218
+ong1 219
+ong2 220
+ong3 221
+ong4 222
+ong5 223
+ong6 224
+ot3 225
+ou 226
+ou1 227
+ou2 228
+ou3 229
+ou4 230
+ou5 231
+ou6 232
+p 233
+s 234
+sil 235
+sp 236
+spl 237
+t 238
+t3 239
+u1 240
+u2 241
+u3 242
+u4 243
+u6 244
+ui1 245
+ui2 246
+ui3 247
+ui4 248
+ui5 249
+ui6 250
+uk 251
+uk1 252
+uk6 253
+un1 254
+un2 255
+un3 256
+un4 257
+un5 258
+un6 259
+ung1 260
+ung2 261
+ung3 262
+ung4 263
+ung5 264
+ung6 265
+ut3 266
+ut6 267
+w 268
+yu1 269
+yu2 270
+yu3 271
+yu4 272
+yu5 273
+yu6 274
+yun1 275
+yun2 276
+yun3 277
+yun4 278
+yun5 279
+yun6 280
+yut3 281
+yut6 282
+z 283
+, 284
+. 285
+? 286
+! 287
+<eos> 288

audio_model_states/fastspeech2_canton_onnx_1.4.0/speaker_id_map.txt

@@ -0,0 +1,20 @@
+G0001 0
+G0002 1
+G0003 2
+G0004 3
+G0005 4
+G0006 5
+G0007 6
+G0008 7
+G0009 8
+G0010 9
+G0051 10
+G0052 11
+G0053 12
+G0054 13
+G0055 14
+G0067 15
+G0068 16
+G0070 17
+G0071 18
+G0072 19

audio_model_states/hifigan_csmsc_onnx_0.2.0/hifigan_csmsc.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c95e5e2e12220590d06bd4c6a3dc44391aa77c1e0d40adc422bbc97f76bdbb
+size 51989194

audio_model_states/whisper-small-cantonese/.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

audio_model_states/whisper-small-cantonese/README.md

@@ -0,0 +1,163 @@
+---
+language:
+- zh
+- yue
+license: apache-2.0
+tags:
+- whisper-event
+- generated_from_trainer
+base_model: openai/whisper-small
+datasets:
+- mozilla-foundation/common_voice_16_0
+- mozilla-foundation/common_voice_17_0
+model-index:
+- name: Whisper Small zh-HK - Alvin
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: mozilla-foundation/common_voice_16_0 yue
+      type: mozilla-foundation/common_voice_16_0
+      config: yue
+      split: test
+      args: yue
+    metrics:
+    - name: Normalized CER
+      type: cer
+      value: 7.93
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Whisper Small Cantonese - Alvin
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Cantonese language. It achieves a 7.93 CER (without punctuations), 9.72 CER (with punctuations) on Common Voice 16.0
+
+## Training and evaluation data
+For training,
+- CantoMap: Winterstein, Grégoire, Tang, Carmen and Lai, Regine (2020) "CantoMap: a Hong Kong Cantonese MapTask Corpus", in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille: European Language Resources Association, p. 2899-2906.
+- Cantonse-ASR: Yu, Tiezheng, Frieske, Rita, Xu, Peng, Cahyawijaya, Samuel, Yiu, Cheuk Tung, Lovenia, Holy, Dai, Wenliang, Barezi, Elham, Chen, Qifeng, Ma, Xiaojuan, Shi, Bertram, Fung, Pascale (2022) "Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset", 2022. Link: https://arxiv.org/pdf/2201.02419.pdf
+
+|Name|# of Hours|
+|--|--|
+|Common Voice 16.0 zh-HK Train|138|
+|Common Voice 16.0 yue Train|85|
+|Common Voice 17.0 yue Train|178|
+|Cantonese-ASR|72|
+|CantoMap|23|
+|[Pseudo-Labelled YouTube Data](https://huggingface.co/datasets/alvanlii/cantonese-youtube-pseudo-transcription)|438|
+
+
+For evaluation, Common Voice 16.0 yue Test set is used.
+
+## Results
+- CER (lower is better): 0.0972
+  - down from 0.1073, 0.1581 in the previous versions
+- CER (punctuations removed): 0.0793
+- GPU Inference with Fast Attention (example below): 0.055s/sample
+  - Note all GPU evaluations are done on RTX 3090 GPU
+- GPU Inference: 0.308s/sample
+- CPU Inference: 2.57s/sample
+- GPU VRAM: ~1.5 GB
+
+
+## Using the Model
+```
+import librosa
+
+import torch
+from transformers import WhisperForConditionalGeneration, WhisperProcessor
+
+y, sr = librosa.load('audio.mp3', sr=16000)
+
+MODEL_NAME = "alvanlii/whisper-small-cantonese"
+
+processor = WhisperProcessor.from_pretrained(MODEL_NAME)
+model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME)
+
+processed_in = processor(y, sampling_rate=sr, return_tensors="pt")
+gout = model.generate(
+    input_features=processed_in.input_features, 
+    output_scores=True, return_dict_in_generate=True
+)
+transcription = processor.batch_decode(gout.sequences, skip_special_tokens=True)[0]
+print(transcription)
+```
+- Alternatively, you can use huggingface pipelines
+```
+from transformers import pipeline
+MODEL_NAME = "alvanlii/whisper-small-cantonese" 
+lang = "zh"
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=30,
+    device=device,
+)
+pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
+text = pipe(file)["text"]
+```
+
+## Model Speedup
+Just add attn_implementation="sdpa" for Flash Attention. 
+```
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    "alvanlii/whisper-small-cantonese",
+    torch_dtype=torch_dtype,
+    low_cpu_mem_usage=True,
+    use_safetensors=True,
+    attn_implementation="sdpa",
+)
+```
+Using Flash Attention reduced the amount of time taken per sample from 0.308s to 0.055s.
+
+## Speculative Decoding
+You can use a bigger model, then use `alvanlii/whisper-small-cantonese` to speed up inference with basically no loss in accuracy.
+```
+model_id = "simonl0909/whisper-large-v2-cantonese"
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id,
+    torch_dtype=torch_dtype,
+    low_cpu_mem_usage=True,
+    use_safetensors=True,
+    attn_implementation="sdpa",
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+assistant_model_id = "alvanlii/whisper-small-cantonese"
+
+assistant_model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    assistant_model_id,
+    torch_dtype=torch_dtype,
+    low_cpu_mem_usage=True,
+    use_safetensors=True,
+    attn_implementation="sdpa",
+)
+
+assistant_model.to(device)
+...
+model.generate(**inputs, use_cache=True, assistant_model=assistant_model)
+```
+In the original `simonl0909/whisper-large-v2-cantonese` model, it runs at 0.714s/sample for a CER of 7.65. \
+Using speculative decoding with `alvanlii/whisper-small-cantonese`, it runs at 0.137s/sample for a CER of 7.67, which is much faster.
+
+## Whisper.cpp
+Uploaded a GGML bin file for Whisper cpp as of June 2024. You can download the bin file [here](https://huggingface.co/alvanlii/whisper-small-cantonese/blob/main/ggml-model.bin) and try it out [here](https://whisper.ggerganov.com/). 
+
+## Whisper CT2
+For use in WhisperX or FasterWhisper, a CT2 file is needed. The converted model is under [here](https://huggingface.co/alvanlii/whisper-small-cantonese/tree/main/cts)
+
+## Training Hyperparameters
+- learning_rate: 5e-5
+- train_batch_size: 25 (on 1 3090 GPU)
+- eval_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 25x4=100
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 15000
+- augmentation: None

audio_model_states/whisper-small-cantonese/added_tokens.json

@@ -0,0 +1,109 @@
+{
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|iw|>": 50279,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
+}

audio_model_states/whisper-small-cantonese/config.json

@@ -0,0 +1,154 @@
+{
+  "_name_or_path": "alvanlii/whisper-small-cantonese",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50360,
+    50361,
+    50362
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

audio_model_states/whisper-small-cantonese/cts/config.json

@@ -0,0 +1,487 @@
+{
+  "alignment_heads": [
+    [
+      6,
+      0
+    ],
+    [
+      6,
+      1
+    ],
+    [
+      6,
+      2
+    ],
+    [
+      6,
+      3
+    ],
+    [
+      6,
+      4
+    ],
+    [
+      6,
+      5
+    ],
+    [
+      6,
+      6
+    ],
+    [
+      6,
+      7
+    ],
+    [
+      6,
+      8
+    ],
+    [
+      6,
+      9
+    ],
+    [
+      6,
+      10
+    ],
+    [
+      6,
+      11
+    ],
+    [
+      7,
+      0
+    ],
+    [
+      7,
+      1
+    ],
+    [
+      7,
+      2
+    ],
+    [
+      7,
+      3
+    ],
+    [
+      7,
+      4
+    ],
+    [
+      7,
+      5
+    ],
+    [
+      7,
+      6
+    ],
+    [
+      7,
+      7
+    ],
+    [
+      7,
+      8
+    ],
+    [
+      7,
+      9
+    ],
+    [
+      7,
+      10
+    ],
+    [
+      7,
+      11
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      1
+    ],
+    [
+      8,
+      2
+    ],
+    [
+      8,
+      3
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      5
+    ],
+    [
+      8,
+      6
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      8,
+      9
+    ],
+    [
+      8,
+      10
+    ],
+    [
+      8,
+      11
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      1
+    ],
+    [
+      9,
+      2
+    ],
+    [
+      9,
+      3
+    ],
+    [
+      9,
+      4
+    ],
+    [
+      9,
+      5
+    ],
+    [
+      9,
+      6
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      8
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      9,
+      10
+    ],
+    [
+      9,
+      11
+    ],
+    [
+      10,
+      0
+    ],
+    [
+      10,
+      1
+    ],
+    [
+      10,
+      2
+    ],
+    [
+      10,
+      3
+    ],
+    [
+      10,
+      4
+    ],
+    [
+      10,
+      5
+    ],
+    [
+      10,
+      6
+    ],
+    [
+      10,
+      7
+    ],
+    [
+      10,
+      8
+    ],
+    [
+      10,
+      9
+    ],
+    [
+      10,
+      10
+    ],
+    [
+      10,
+      11
+    ],
+    [
+      11,
+      0
+    ],
+    [
+      11,
+      1
+    ],
+    [
+      11,
+      2
+    ],
+    [
+      11,
+      3
+    ],
+    [
+      11,
+      4
+    ],
+    [
+      11,
+      5
+    ],
+    [
+      11,
+      6
+    ],
+    [
+      11,
+      7
+    ],
+    [
+      11,
+      8
+    ],
+    [
+      11,
+      9
+    ],
+    [
+      11,
+      10
+    ],
+    [
+      11,
+      11
+    ]
+  ],
+  "lang_ids": [
+    50259,
+    50260,
+    50261,
+    50262,
+    50263,
+    50264,
+    50265,
+    50266,
+    50267,
+    50268,
+    50269,
+    50270,
+    50271,
+    50272,
+    50273,
+    50274,
+    50275,
+    50276,
+    50277,
+    50278,
+    50279,
+    50280,
+    50281,
+    50282,
+    50283,
+    50284,
+    50285,
+    50286,
+    50287,
+    50288,
+    50289,
+    50290,
+    50291,
+    50292,
+    50293,
+    50294,
+    50295,
+    50296,
+    50297,
+    50298,
+    50299,
+    50300,
+    50301,
+    50302,
+    50303,
+    50304,
+    50305,
+    50306,
+    50307,
+    50308,
+    50309,
+    50310,
+    50311,
+    50312,
+    50313,
+    50314,
+    50315,
+    50316,
+    50317,
+    50318,
+    50319,
+    50320,
+    50321,
+    50322,
+    50323,
+    50324,
+    50325,
+    50326,
+    50327,
+    50328,
+    50329,
+    50330,
+    50331,
+    50332,
+    50333,
+    50334,
+    50335,
+    50336,
+    50337,
+    50338,
+    50339,
+    50340,
+    50341,
+    50342,
+    50343,
+    50344,
+    50345,
+    50346,
+    50347,
+    50348,
+    50349,
+    50350,
+    50351,
+    50352,
+    50353,
+    50354,
+    50355,
+    50356,
+    50357
+  ],
+  "suppress_ids": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

audio_model_states/whisper-small-cantonese/cts/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d343caa7ef827ddb60bc2c1c8c741b29d2bd99d5387aa5c6f96cbd26f6804b34
+size 967072097

audio_model_states/whisper-small-cantonese/cts/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

audio_model_states/whisper-small-cantonese/generation_config.json

@@ -0,0 +1,103 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false
+}

audio_model_states/whisper-small-cantonese/ggml-model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6ddf83921733fd96b0bbb4850ae57c330a1049ab35252bf36b1d339835d2bf
+size 487601967

audio_model_states/whisper-small-cantonese/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde842c011b43b2a7b988ad9b9f1a082731bc29c3d58b0cdffa3e71252ef7256
+size 966995080

audio_model_states/whisper-small-cantonese/normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+  "channelling": "channeling",
+  "characterise": "characterize",
+  "characterised": "characterized",
+  "characterises": "characterizes",
+  "characterising": "characterizing",
+  "cheque": "check",
+  "chequebook": "checkbook",
+  "chequebooks": "checkbooks",
+  "chequered": "checkered",
+  "cheques": "checks",
+  "chilli": "chili",
+  "chimaera": "chimera",
+  "chimaeras": "chimeras",
+  "chiselled": "chiseled",
+  "chiselling": "chiseling",
+  "circularise": "circularize",
+  "circularised": "circularized",
+  "circularises": "circularizes",
+  "circularising": "circularizing",
+  "civilise": "civilize",
+  "civilised": "civilized",
+  "civilises": "civilizes",
+  "civilising": "civilizing",
+  "clamour": "clamor",
+  "clamoured": "clamored",
+  "clamouring": "clamoring",
+  "clamours": "clamors",
+  "clangour": "clangor",
+  "clarinettist": "clarinetist",
+  "clarinettists": "clarinetists",
+  "collectivise": "collectivize",
+  "collectivised": "collectivized",
+  "collectivises": "collectivizes",
+  "collectivising": "collectivizing",
+  "colonisation": "colonization",
+  "colonise": "colonize",
+  "colonised": "colonized",
+  "coloniser": "colonizer",
+  "colonisers": "colonizers",
+  "colonises": "colonizes",
+  "colonising": "colonizing",
+  "colour": "color",
+  "colourant": "colorant",
+  "colourants": "colorants",
+  "coloured": "colored",
+  "coloureds": "coloreds",
+  "colourful": "colorful",
+  "colourfully": "colorfully",
+  "colouring": "coloring",
+  "colourize": "colorize",
+  "colourized": "colorized",
+  "colourizes": "colorizes",
+  "colourizing": "colorizing",
+  "colourless": "colorless",
+  "colours": "colors",
+  "commercialise": "commercialize",
+  "commercialised": "commercialized",
+  "commercialises": "commercializes",
+  "commercialising": "commercializing",
+  "compartmentalise": "compartmentalize",
+  "compartmentalised": "compartmentalized",
+  "compartmentalises": "compartmentalizes",
+  "compartmentalising": "compartmentalizing",
+  "computerise": "computerize",
+  "computerised": "computerized",
+  "computerises": "computerizes",
+  "computerising": "computerizing",
+  "conceptualise": "conceptualize",
+  "conceptualised": "conceptualized",
+  "conceptualises": "conceptualizes",
+  "conceptualising": "conceptualizing",
+  "connexion": "connection",
+  "connexions": "connections",
+  "contextualise": "contextualize",
+  "contextualised": "contextualized",
+  "contextualises": "contextualizes",
+  "contextualising": "contextualizing",
+  "cosier": "cozier",
+  "cosies": "cozies",
+  "cosiest": "coziest",
+  "cosily": "cozily",
+  "cosiness": "coziness",
+  "cosy": "cozy",
+  "councillor": "councilor",
+  "councillors": "councilors",
+  "counselled": "counseled",
+  "counselling": "counseling",
+  "counsellor": "counselor",
+  "counsellors": "counselors",
+  "crenelated": "crenellated",
+  "criminalise": "criminalize",
+  "criminalised": "criminalized",
+  "criminalises": "criminalizes",
+  "criminalising": "criminalizing",
+  "criticise": "criticize",
+  "criticised": "criticized",
+  "criticises": "criticizes",
+  "criticising": "criticizing",
+  "crueller": "crueler",
+  "cruellest": "cruelest",
+  "crystallisation": "crystallization",
+  "crystallise": "crystallize",
+  "crystallised": "crystallized",
+  "crystallises": "crystallizes",
+  "crystallising": "crystallizing",
+  "cudgelled": "cudgeled",
+  "cudgelling": "cudgeling",
+  "customise": "customize",
+  "customised": "customized",
+  "customises": "customizes",
+  "customising": "customizing",
+  "cypher": "cipher",
+  "cyphers": "ciphers",
+  "decentralisation": "decentralization",
+  "decentralise": "decentralize",
+  "decentralised": "decentralized",
+  "decentralises": "decentralizes",
+  "decentralising": "decentralizing",
+  "decriminalisation": "decriminalization",
+  "decriminalise": "decriminalize",
+  "decriminalised": "decriminalized",
+  "decriminalises": "decriminalizes",
+  "decriminalising": "decriminalizing",
+  "defence": "defense",
+  "defenceless": "defenseless",
+  "defences": "defenses",
+  "dehumanisation": "dehumanization",
+  "dehumanise": "dehumanize",
+  "dehumanised": "dehumanized",
+  "dehumanises": "dehumanizes",
+  "dehumanising": "dehumanizing",
+  "demeanour": "demeanor",
+  "demilitarisation": "demilitarization",
+  "demilitarise": "demilitarize",
+  "demilitarised": "demilitarized",
+  "demilitarises": "demilitarizes",
+  "demilitarising": "demilitarizing",
+  "demobilisation": "demobilization",
+  "demobilise": "demobilize",
+  "demobilised": "demobilized",
+  "demobilises": "demobilizes",
+  "demobilising": "demobilizing",
+  "democratisation": "democratization",
+  "democratise": "democratize",
+  "democratised": "democratized",
+  "democratises": "democratizes",
+  "democratising": "democratizing",
+  "demonise": "demonize",
+  "demonised": "demonized",
+  "demonises": "demonizes",
+  "demonising": "demonizing",
+  "demoralisation": "demoralization",
+  "demoralise": "demoralize",
+  "demoralised": "demoralized",
+  "demoralises": "demoralizes",
+  "demoralising": "demoralizing",
+  "denationalisation": "denationalization",
+  "denationalise": "denationalize",
+  "denationalised": "denationalized",
+  "denationalises": "denationalizes",
+  "denationalising": "denationalizing",
+  "deodorise": "deodorize",
+  "deodorised": "deodorized",
+  "deodorises": "deodorizes",
+  "deodorising": "deodorizing",
+  "depersonalise": "depersonalize",
+  "depersonalised": "depersonalized",
+  "depersonalises": "depersonalizes",
+  "depersonalising": "depersonalizing",
+  "deputise": "deputize",
+  "deputised": "deputized",
+  "deputises": "deputizes",
+  "deputising": "deputizing",
+  "desensitisation": "desensitization",
+  "desensitise": "desensitize",
+  "desensitised": "desensitized",
+  "desensitises": "desensitizes",
+  "desensitising": "desensitizing",
+  "destabilisation": "destabilization",
+  "destabilise": "destabilize",
+  "destabilised": "destabilized",
+  "destabilises": "destabilizes",
+  "destabilising": "destabilizing",
+  "dialled": "dialed",
+  "dialling": "dialing",
+  "dialogue": "dialog",
+  "dialogues": "dialogs",
+  "diarrhoea": "diarrhea",
+  "digitise": "digitize",
+  "digitised": "digitized",
+  "digitises": "digitizes",
+  "digitising": "digitizing",
+  "disc": "disk",
+  "discolour": "discolor",
+  "discoloured": "discolored",
+  "discolouring": "discoloring",
+  "discolours": "discolors",
+  "discs": "disks",
+  "disembowelled": "disemboweled",
+  "disembowelling": "disemboweling",
+  "disfavour": "disfavor",
+  "dishevelled": "disheveled",
+  "dishonour": "dishonor",
+  "dishonourable": "dishonorable",
+  "dishonourably": "dishonorably",
+  "dishonoured": "dishonored",
+  "dishonouring": "dishonoring",
+  "dishonours": "dishonors",
+  "disorganisation": "disorganization",
+  "disorganised": "disorganized",
+  "distil": "distill",
+  "distils": "distills",
+  "dramatisation": "dramatization",
+  "dramatisations": "dramatizations",
+  "dramatise": "dramatize",
+  "dramatised": "dramatized",
+  "dramatises": "dramatizes",
+  "dramatising": "dramatizing",
+  "draught": "draft",
+  "draughtboard": "draftboard",
+  "draughtboards": "draftboards",
+  "draughtier": "draftier",
+  "draughtiest": "draftiest",
+  "draughts": "drafts",
+  "draughtsman": "draftsman",
+  "draughtsmanship": "draftsmanship",
+  "draughtsmen": "draftsmen",
+  "draughtswoman": "draftswoman",
+  "draughtswomen": "draftswomen",
+  "draughty": "drafty",
+  "drivelled": "driveled",
+  "drivelling": "driveling",
+  "duelled": "dueled",
+  "duelling": "dueling",
+  "economise": "economize",
+  "economised": "economized",
+  "economises": "economizes",
+  "economising": "economizing",
+  "editorialise": "editorialize",
+  "editorialised": "editorialized",
+  "editorialises": "editorializes",
+  "editorialising": "editorializing",
+  "edoema": "edema",
+  "empathise": "empathize",
+  "empathised": "empathized",
+  "empathises": "empathizes",
+  "empathising": "empathizing",
+  "emphasise": "emphasize",
+  "emphasised": "emphasized",
+  "emphasises": "emphasizes",
+  "emphasising": "emphasizing",
+  "enamelled": "enameled",
+  "enamelling": "enameling",
+  "enamoured": "enamored",
+  "encyclopaedia": "encyclopedia",
+  "encyclopaedias": "encyclopedias",
+  "encyclopaedic": "encyclopedic",
+  "endeavour": "endeavor",
+  "endeavoured": "endeavored",
+  "endeavouring": "endeavoring",
+  "endeavours": "endeavors",
+  "energise": "energize",
+  "energised": "energized",
+  "energises": "energizes",
+  "energising": "energizing",
+  "enrol": "enroll",
+  "enrols": "enrolls",
+  "enthral": "enthrall",
+  "enthrals": "enthralls",
+  "epaulette": "epaulet",
+  "epaulettes": "epaulets",
+  "epicentre": "epicenter",
+  "epicentres": "epicenters",
+  "epilogue": "epilog",
+  "epilogues": "epilogs",
+  "epitomise": "epitomize",
+  "epitomised": "epitomized",
+  "epitomises": "epitomizes",
+  "epitomising": "epitomizing",
+  "equalisation": "equalization",
+  "equalise": "equalize",
+  "equalised": "equalized",
+  "equaliser": "equalizer",
+  "equalisers": "equalizers",
+  "equalises": "equalizes",
+  "equalising": "equalizing",
+  "eulogise": "eulogize",
+  "eulogised": "eulogized",
+  "eulogises": "eulogizes",
+  "eulogising": "eulogizing",
+  "evangelise": "evangelize",
+  "evangelised": "evangelized",
+  "evangelises": "evangelizes",
+  "evangelising": "evangelizing",
+  "exorcise": "exorcize",
+  "exorcised": "exorcized",
+  "exorcises": "exorcizes",
+  "exorcising": "exorcizing",
+  "extemporisation": "extemporization",
+  "extemporise": "extemporize",
+  "extemporised": "extemporized",
+  "extemporises": "extemporizes",
+  "extemporising": "extemporizing",
+  "externalisation": "externalization",
+  "externalisations": "externalizations",
+  "externalise": "externalize",
+  "externalised": "externalized",
+  "externalises": "externalizes",
+  "externalising": "externalizing",
+  "factorise": "factorize",
+  "factorised": "factorized",
+  "factorises": "factorizes",
+  "factorising": "factorizing",
+  "faecal": "fecal",
+  "faeces": "feces",
+  "familiarisation": "familiarization",
+  "familiarise": "familiarize",
+  "familiarised": "familiarized",
+  "familiarises": "familiarizes",
+  "familiarising": "familiarizing",
+  "fantasise": "fantasize",
+  "fantasised": "fantasized",
+  "fantasises": "fantasizes",
+  "fantasising": "fantasizing",
+  "favour": "favor",
+  "favourable": "favorable",
+  "favourably": "favorably",
+  "favoured": "favored",
+  "favouring": "favoring",
+  "favourite": "favorite",
+  "favourites": "favorites",
+  "favouritism": "favoritism",
+  "favours": "favors",
+  "feminise": "feminize",
+  "feminised": "feminized",
+  "feminises": "feminizes",
+  "feminising": "feminizing",
+  "fertilisation": "fertilization",
+  "fertilise": "fertilize",
+  "fertilised": "fertilized",
+  "fertiliser": "fertilizer",
+  "fertilisers": "fertilizers",
+  "fertilises": "fertilizes",
+  "fertilising": "fertilizing",
+  "fervour": "fervor",
+  "fibre": "fiber",
+  "fibreglass": "fiberglass",
+  "fibres": "fibers",
+  "fictionalisation": "fictionalization",
+  "fictionalisations": "fictionalizations",
+  "fictionalise": "fictionalize",
+  "fictionalised": "fictionalized",
+  "fictionalises": "fictionalizes",
+  "fictionalising": "fictionalizing",
+  "fillet": "filet",
+  "filleted": "fileted",
+  "filleting": "fileting",
+  "fillets": "filets",
+  "finalisation": "finalization",
+  "finalise": "finalize",
+  "finalised": "finalized",
+  "finalises": "finalizes",
+  "finalising": "finalizing",
+  "flautist": "flutist",
+  "flautists": "flutists",
+  "flavour": "flavor",
+  "flavoured": "flavored",
+  "flavouring": "flavoring",
+  "flavourings": "flavorings",
+  "flavourless": "flavorless",
+  "flavours": "flavors",
+  "flavoursome": "flavorsome",
+  "flyer / flier": "flier / flyer",
+  "foetal": "fetal",
+  "foetid": "fetid",
+  "foetus": "fetus",
+  "foetuses": "fetuses",
+  "formalisation": "formalization",
+  "formalise": "formalize",
+  "formalised": "formalized",
+  "formalises": "formalizes",
+  "formalising": "formalizing",
+  "fossilisation": "fossilization",
+  "fossilise": "fossilize",
+  "fossilised": "fossilized",
+  "fossilises": "fossilizes",
+  "fossilising": "fossilizing",
+  "fraternisation": "fraternization",
+  "fraternise": "fraternize",
+  "fraternised": "fraternized",
+  "fraternises": "fraternizes",
+  "fraternising": "fraternizing",
+  "fulfil": "fulfill",
+  "fulfilment": "fulfillment",
+  "fulfils": "fulfills",
+  "funnelled": "funneled",
+  "funnelling": "funneling",
+  "gage": "gauge",
+  "gaged": "gauged",
+  "gages": "gauges",
+  "gaging": "gauging",
+  "galvanise": "galvanize",
+  "galvanised": "galvanized",
+  "galvanises": "galvanizes",
+  "galvanising": "galvanizing",
+  "gambolled": "gamboled",
+  "gambolling": "gamboling",
+  "gaol": "jail",
+  "gaolbird": "jailbird",
+  "gaolbirds": "jailbirds",
+  "gaolbreak": "jailbreak",
+  "gaolbreaks": "jailbreaks",
+  "gaoled": "jailed",
+  "gaoler": "jailer",
+  "gaolers": "jailers",
+  "gaoling": "jailing",
+  "gaols": "jails",
+  "gasses": "gases",
+  "generalisation": "generalization",
+  "generalisations": "generalizations",
+  "generalise": "generalize",
+  "generalised": "generalized",
+  "generalises": "generalizes",
+  "generalising": "generalizing",
+  "ghettoise": "ghettoize",
+  "ghettoised": "ghettoized",
+  "ghettoises": "ghettoizes",
+  "ghettoising": "ghettoizing",
+  "gipsies": "gypsies",
+  "glamor": "glamour",
+  "glamorise": "glamorize",
+  "glamorised": "glamorized",
+  "glamorises": "glamorizes",
+  "glamorising": "glamorizing",
+  "globalisation": "globalization",
+  "globalise": "globalize",
+  "globalised": "globalized",
+  "globalises": "globalizes",
+  "globalising": "globalizing",
+  "glueing": "gluing",
+  "goitre": "goiter",
+  "goitres": "goiters",
+  "gonorrhoea": "gonorrhea",
+  "gramme": "gram",
+  "grammes": "grams",
+  "gravelled": "graveled",
+  "grey": "gray",
+  "greyed": "grayed",
+  "greying": "graying",
+  "greyish": "grayish",
+  "greyness": "grayness",
+  "greys": "grays",
+  "grovelled": "groveled",
+  "grovelling": "groveling",
+  "groyne": "groin",
+  "groynes": "groins",
+  "gruelling": "grueling",
+  "gruellingly": "gruelingly",
+  "gryphon": "griffin",
+  "gryphons": "griffins",
+  "gynaecological": "gynecological",
+  "gynaecologist": "gynecologist",
+  "gynaecologists": "gynecologists",
+  "gynaecology": "gynecology",
+  "haematological": "hematological",
+  "haematologist": "hematologist",
+  "haematologists": "hematologists",
+  "haematology": "hematology",
+  "haemoglobin": "hemoglobin",
+  "haemophilia": "hemophilia",
+  "haemophiliac": "hemophiliac",
+  "haemophiliacs": "hemophiliacs",
+  "haemorrhage": "hemorrhage",
+  "haemorrhaged": "hemorrhaged",
+  "haemorrhages": "hemorrhages",
+  "haemorrhaging": "hemorrhaging",
+  "haemorrhoids": "hemorrhoids",
+  "harbour": "harbor",
+  "harboured": "harbored",
+  "harbouring": "harboring",
+  "harbours": "harbors",
+  "harmonisation": "harmonization",
+  "harmonise": "harmonize",
+  "harmonised": "harmonized",
+  "harmonises": "harmonizes",
+  "harmonising": "harmonizing",
+  "homoeopath": "homeopath",
+  "homoeopathic": "homeopathic",
+  "homoeopaths": "homeopaths",
+  "homoeopathy": "homeopathy",
+  "homogenise": "homogenize",
+  "homogenised": "homogenized",
+  "homogenises": "homogenizes",
+  "homogenising": "homogenizing",
+  "honour": "honor",
+  "honourable": "honorable",
+  "honourably": "honorably",
+  "honoured": "honored",
+  "honouring": "honoring",
+  "honours": "honors",
+  "hospitalisation": "hospitalization",
+  "hospitalise": "hospitalize",
+  "hospitalised": "hospitalized",
+  "hospitalises": "hospitalizes",
+  "hospitalising": "hospitalizing",
+  "humanise": "humanize",
+  "humanised": "humanized",
+  "humanises": "humanizes",
+  "humanising": "humanizing",
+  "humour": "humor",
+  "humoured": "humored",
+  "humouring": "humoring",
+  "humourless": "humorless",
+  "humours": "humors",
+  "hybridise": "hybridize",
+  "hybridised": "hybridized",
+  "hybridises": "hybridizes",
+  "hybridising": "hybridizing",
+  "hypnotise": "hypnotize",
+  "hypnotised": "hypnotized",
+  "hypnotises": "hypnotizes",
+  "hypnotising": "hypnotizing",
+  "hypothesise": "hypothesize",
+  "hypothesised": "hypothesized",
+  "hypothesises": "hypothesizes",
+  "hypothesising": "hypothesizing",
+  "idealisation": "idealization",
+  "idealise": "idealize",
+  "idealised": "idealized",
+  "idealises": "idealizes",
+  "idealising": "idealizing",
+  "idolise": "idolize",
+  "idolised": "idolized",
+  "idolises": "idolizes",
+  "idolising": "idolizing",
+  "immobilisation": "immobilization",
+  "immobilise": "immobilize",
+  "immobilised": "immobilized",
+  "immobiliser": "immobilizer",
+  "immobilisers": "immobilizers",
+  "immobilises": "immobilizes",
+  "immobilising": "immobilizing",
+  "immortalise": "immortalize",
+  "immortalised": "immortalized",
+  "immortalises": "immortalizes",
+  "immortalising": "immortalizing",
+  "immunisation": "immunization",
+  "immunise": "immunize",
+  "immunised": "immunized",
+  "immunises": "immunizes",
+  "immunising": "immunizing",
+  "impanelled": "impaneled",
+  "impanelling": "impaneling",
+  "imperilled": "imperiled",
+  "imperilling": "imperiling",
+  "individualise": "individualize",
+  "individualised": "individualized",
+  "individualises": "individualizes",
+  "individualising": "individualizing",
+  "industrialise": "industrialize",
+  "industrialised": "industrialized",
+  "industrialises": "industrializes",
+  "industrialising": "industrializing",
+  "inflexion": "inflection",
+  "inflexions": "inflections",
+  "initialise": "initialize",
+  "initialised": "initialized",
+  "initialises": "initializes",
+  "initialising": "initializing",
+  "initialled": "initialed",
+  "initialling": "initialing",
+  "instal": "install",
+  "instalment": "installment",
+  "instalments": "installments",
+  "instals": "installs",
+  "instil": "instill",
+  "instils": "instills",
+  "institutionalisation": "institutionalization",
+  "institutionalise": "institutionalize",
+  "institutionalised": "institutionalized",
+  "institutionalises": "institutionalizes",
+  "institutionalising": "institutionalizing",
+  "intellectualise": "intellectualize",
+  "intellectualised": "intellectualized",
+  "intellectualises": "intellectualizes",
+  "intellectualising": "intellectualizing",
+  "internalisation": "internalization",
+  "internalise": "internalize",
+  "internalised": "internalized",
+  "internalises": "internalizes",
+  "internalising": "internalizing",
+  "internationalisation": "internationalization",
+  "internationalise": "internationalize",
+  "internationalised": "internationalized",
+  "internationalises": "internationalizes",
+  "internationalising": "internationalizing",
+  "ionisation": "ionization",
+  "ionise": "ionize",
+  "ionised": "ionized",
+  "ioniser": "ionizer",
+  "ionisers": "ionizers",
+  "ionises": "ionizes",
+  "ionising": "ionizing",
+  "italicise": "italicize",
+  "italicised": "italicized",
+  "italicises": "italicizes",
+  "italicising": "italicizing",
+  "itemise": "itemize",
+  "itemised": "itemized",
+  "itemises": "itemizes",
+  "itemising": "itemizing",
+  "jeopardise": "jeopardize",
+  "jeopardised": "jeopardized",
+  "jeopardises": "jeopardizes",
+  "jeopardising": "jeopardizing",
+  "jewelled": "jeweled",
+  "jeweller": "jeweler",
+  "jewellers": "jewelers",
+  "jewellery": "jewelry",
+  "judgement": "judgment",
+  "kilogramme": "kilogram",
+  "kilogrammes": "kilograms",
+  "kilometre": "kilometer",
+  "kilometres": "kilometers",
+  "labelled": "labeled",
+  "labelling": "labeling",
+  "labour": "labor",
+  "laboured": "labored",
+  "labourer": "laborer",
+  "labourers": "laborers",
+  "labouring": "laboring",
+  "labours": "labors",
+  "lacklustre": "lackluster",
+  "legalisation": "legalization",
+  "legalise": "legalize",
+  "legalised": "legalized",
+  "legalises": "legalizes",
+  "legalising": "legalizing",
+  "legitimise": "legitimize",
+  "legitimised": "legitimized",
+  "legitimises": "legitimizes",
+  "legitimising": "legitimizing",
+  "leukaemia": "leukemia",
+  "levelled": "leveled",
+  "leveller": "leveler",
+  "levellers": "levelers",
+  "levelling": "leveling",
+  "libelled": "libeled",
+  "libelling": "libeling",
+  "libellous": "libelous",
+  "liberalisation": "liberalization",
+  "liberalise": "liberalize",
+  "liberalised": "liberalized",
+  "liberalises": "liberalizes",
+  "liberalising": "liberalizing",
+  "licence": "license",
+  "licenced": "licensed",
+  "licences": "licenses",
+  "licencing": "licensing",
+  "likeable": "likable",
+  "lionisation": "lionization",
+  "lionise": "lionize",
+  "lionised": "lionized",
+  "lionises": "lionizes",
+  "lionising": "lionizing",
+  "liquidise": "liquidize",
+  "liquidised": "liquidized",
+  "liquidiser": "liquidizer",
+  "liquidisers": "liquidizers",
+  "liquidises": "liquidizes",
+  "liquidising": "liquidizing",
+  "litre": "liter",
+  "litres": "liters",
+  "localise": "localize",
+  "localised": "localized",
+  "localises": "localizes",
+  "localising": "localizing",
+  "louvre": "louver",
+  "louvred": "louvered",
+  "louvres": "louvers",
+  "lustre": "luster",
+  "magnetise": "magnetize",
+  "magnetised": "magnetized",
+  "magnetises": "magnetizes",
+  "magnetising": "magnetizing",
+  "manoeuvrability": "maneuverability",
+  "manoeuvrable": "maneuverable",
+  "manoeuvre": "maneuver",
+  "manoeuvred": "maneuvered",
+  "manoeuvres": "maneuvers",
+  "manoeuvring": "maneuvering",
+  "manoeuvrings": "maneuverings",
+  "marginalisation": "marginalization",
+  "marginalise": "marginalize",
+  "marginalised": "marginalized",
+  "marginalises": "marginalizes",
+  "marginalising": "marginalizing",
+  "marshalled": "marshaled",
+  "marshalling": "marshaling",
+  "marvelled": "marveled",
+  "marvelling": "marveling",
+  "marvellous": "marvelous",
+  "marvellously": "marvelously",
+  "materialisation": "materialization",
+  "materialise": "materialize",
+  "materialised": "materialized",
+  "materialises": "materializes",
+  "materialising": "materializing",
+  "maximisation": "maximization",
+  "maximise": "maximize",
+  "maximised": "maximized",
+  "maximises": "maximizes",
+  "maximising": "maximizing",
+  "meagre": "meager",
+  "mechanisation": "mechanization",
+  "mechanise": "mechanize",
+  "mechanised": "mechanized",
+  "mechanises": "mechanizes",
+  "mechanising": "mechanizing",
+  "mediaeval": "medieval",
+  "memorialise": "memorialize",
+  "memorialised": "memorialized",
+  "memorialises": "memorializes",
+  "memorialising": "memorializing",
+  "memorise": "memorize",
+  "memorised": "memorized",
+  "memorises": "memorizes",
+  "memorising": "memorizing",
+  "mesmerise": "mesmerize",
+  "mesmerised": "mesmerized",
+  "mesmerises": "mesmerizes",
+  "mesmerising": "mesmerizing",
+  "metabolise": "metabolize",
+  "metabolised": "metabolized",
+  "metabolises": "metabolizes",
+  "metabolising": "metabolizing",
+  "metre": "meter",
+  "metres": "meters",
+  "mhm": "hmm",
+  "micrometre": "micrometer",
+  "micrometres": "micrometers",
+  "militarise": "militarize",
+  "militarised": "militarized",
+  "militarises": "militarizes",
+  "militarising": "militarizing",
+  "milligramme": "milligram",
+  "milligrammes": "milligrams",
+  "millilitre": "milliliter",
+  "millilitres": "milliliters",
+  "millimetre": "millimeter",
+  "millimetres": "millimeters",
+  "miniaturisation": "miniaturization",
+  "miniaturise": "miniaturize",
+  "miniaturised": "miniaturized",
+  "miniaturises": "miniaturizes",
+  "miniaturising": "miniaturizing",
+  "minibusses": "minibuses",
+  "minimise": "minimize",
+  "minimised": "minimized",
+  "minimises": "minimizes",
+  "minimising": "minimizing",
+  "misbehaviour": "misbehavior",
+  "misdemeanour": "misdemeanor",
+  "misdemeanours": "misdemeanors",
+  "misspelt": "misspelled",
+  "mitre": "miter",
+  "mitres": "miters",
+  "mm": "hmm",
+  "mmm": "hmm",
+  "mobilisation": "mobilization",
+  "mobilise": "mobilize",
+  "mobilised": "mobilized",
+  "mobilises": "mobilizes",
+  "mobilising": "mobilizing",
+  "modelled": "modeled",
+  "modeller": "modeler",
+  "modellers": "modelers",
+  "modelling": "modeling",
+  "modernise": "modernize",
+  "modernised": "modernized",
+  "modernises": "modernizes",
+  "modernising": "modernizing",
+  "moisturise": "moisturize",
+  "moisturised": "moisturized",
+  "moisturiser": "moisturizer",
+  "moisturisers": "moisturizers",
+  "moisturises": "moisturizes",
+  "moisturising": "moisturizing",
+  "monologue": "monolog",
+  "monologues": "monologs",
+  "monopolisation": "monopolization",
+  "monopolise": "monopolize",
+  "monopolised": "monopolized",
+  "monopolises": "monopolizes",
+  "monopolising": "monopolizing",
+  "moralise": "moralize",
+  "moralised": "moralized",
+  "moralises": "moralizes",
+  "moralising": "moralizing",
+  "motorised": "motorized",
+  "mould": "mold",
+  "moulded": "molded",
+  "moulder": "molder",
+  "mouldered": "moldered",
+  "mouldering": "moldering",
+  "moulders": "molders",
+  "mouldier": "moldier",
+  "mouldiest": "moldiest",
+  "moulding": "molding",
+  "mouldings": "moldings",
+  "moulds": "molds",
+  "mouldy": "moldy",
+  "moult": "molt",
+  "moulted": "molted",
+  "moulting": "molting",
+  "moults": "molts",
+  "moustache": "mustache",
+  "moustached": "mustached",
+  "moustaches": "mustaches",
+  "moustachioed": "mustachioed",
+  "multicoloured": "multicolored",
+  "nationalisation": "nationalization",
+  "nationalisations": "nationalizations",
+  "nationalise": "nationalize",
+  "nationalised": "nationalized",
+  "nationalises": "nationalizes",
+  "nationalising": "nationalizing",
+  "naturalisation": "naturalization",
+  "naturalise": "naturalize",
+  "naturalised": "naturalized",
+  "naturalises": "naturalizes",
+  "naturalising": "naturalizing",
+  "neighbour": "neighbor",
+  "neighbourhood": "neighborhood",
+  "neighbourhoods": "neighborhoods",
+  "neighbouring": "neighboring",
+  "neighbourliness": "neighborliness",
+  "neighbourly": "neighborly",
+  "neighbours": "neighbors",
+  "neutralisation": "neutralization",
+  "neutralise": "neutralize",
+  "neutralised": "neutralized",
+  "neutralises": "neutralizes",
+  "neutralising": "neutralizing",
+  "normalisation": "normalization",
+  "normalise": "normalize",
+  "normalised": "normalized",
+  "normalises": "normalizes",
+  "normalising": "normalizing",
+  "odour": "odor",
+  "odourless": "odorless",
+  "odours": "odors",
+  "oesophagus": "esophagus",
+  "oesophaguses": "esophaguses",
+  "oestrogen": "estrogen",
+  "offence": "offense",
+  "offences": "offenses",
+  "omelette": "omelet",
+  "omelettes": "omelets",
+  "optimise": "optimize",
+  "optimised": "optimized",
+  "optimises": "optimizes",
+  "optimising": "optimizing",
+  "organisation": "organization",
+  "organisational": "organizational",
+  "organisations": "organizations",
+  "organise": "organize",
+  "organised": "organized",
+  "organiser": "organizer",
+  "organisers": "organizers",
+  "organises": "organizes",
+  "organising": "organizing",
+  "orthopaedic": "orthopedic",
+  "orthopaedics": "orthopedics",
+  "ostracise": "ostracize",
+  "ostracised": "ostracized",
+  "ostracises": "ostracizes",
+  "ostracising": "ostracizing",
+  "outmanoeuvre": "outmaneuver",
+  "outmanoeuvred": "outmaneuvered",
+  "outmanoeuvres": "outmaneuvers",
+  "outmanoeuvring": "outmaneuvering",
+  "overemphasise": "overemphasize",
+  "overemphasised": "overemphasized",
+  "overemphasises": "overemphasizes",
+  "overemphasising": "overemphasizing",
+  "oxidisation": "oxidization",
+  "oxidise": "oxidize",
+  "oxidised": "oxidized",
+  "oxidises": "oxidizes",
+  "oxidising": "oxidizing",
+  "paederast": "pederast",
+  "paederasts": "pederasts",
+  "paediatric": "pediatric",
+  "paediatrician": "pediatrician",
+  "paediatricians": "pediatricians",
+  "paediatrics": "pediatrics",
+  "paedophile": "pedophile",
+  "paedophiles": "pedophiles",
+  "paedophilia": "pedophilia",
+  "palaeolithic": "paleolithic",
+  "palaeontologist": "paleontologist",
+  "palaeontologists": "paleontologists",
+  "palaeontology": "paleontology",
+  "panelled": "paneled",
+  "panelling": "paneling",
+  "panellist": "panelist",
+  "panellists": "panelists",
+  "paralyse": "paralyze",
+  "paralysed": "paralyzed",
+  "paralyses": "paralyzes",
+  "paralysing": "paralyzing",
+  "parcelled": "parceled",
+  "parcelling": "parceling",
+  "parlour": "parlor",
+  "parlours": "parlors",
+  "particularise": "particularize",
+  "particularised": "particularized",
+  "particularises": "particularizes",
+  "particularising": "particularizing",
+  "passivisation": "passivization",
+  "passivise": "passivize",
+  "passivised": "passivized",
+  "passivises": "passivizes",
+  "passivising": "passivizing",
+  "pasteurisation": "pasteurization",
+  "pasteurise": "pasteurize",
+  "pasteurised": "pasteurized",
+  "pasteurises": "pasteurizes",
+  "pasteurising": "pasteurizing",
+  "patronise": "patronize",
+  "patronised": "patronized",
+  "patronises": "patronizes",
+  "patronising": "patronizing",
+  "patronisingly": "patronizingly",
+  "pedalled": "pedaled",
+  "pedalling": "pedaling",
+  "pedestrianisation": "pedestrianization",
+  "pedestrianise": "pedestrianize",
+  "pedestrianised": "pedestrianized",
+  "pedestrianises": "pedestrianizes",
+  "pedestrianising": "pedestrianizing",
+  "penalise": "penalize",
+  "penalised": "penalized",
+  "penalises": "penalizes",
+  "penalising": "penalizing",
+  "pencilled": "penciled",
+  "pencilling": "penciling",
+  "personalise": "personalize",
+  "personalised": "personalized",
+  "personalises": "personalizes",
+  "personalising": "personalizing",
+  "pharmacopoeia": "pharmacopeia",
+  "pharmacopoeias": "pharmacopeias",
+  "philosophise": "philosophize",
+  "philosophised": "philosophized",
+  "philosophises": "philosophizes",
+  "philosophising": "philosophizing",
+  "philtre": "filter",
+  "philtres": "filters",
+  "phoney": "phony",
+  "plagiarise": "plagiarize",
+  "plagiarised": "plagiarized",
+  "plagiarises": "plagiarizes",
+  "plagiarising": "plagiarizing",
+  "plough": "plow",
+  "ploughed": "plowed",
+  "ploughing": "plowing",
+  "ploughman": "plowman",
+  "ploughmen": "plowmen",
+  "ploughs": "plows",
+  "ploughshare": "plowshare",
+  "ploughshares": "plowshares",
+  "polarisation": "polarization",
+  "polarise": "polarize",
+  "polarised": "polarized",
+  "polarises": "polarizes",
+  "polarising": "polarizing",
+  "politicisation": "politicization",
+  "politicise": "politicize",
+  "politicised": "politicized",
+  "politicises": "politicizes",
+  "politicising": "politicizing",
+  "popularisation": "popularization",
+  "popularise": "popularize",
+  "popularised": "popularized",
+  "popularises": "popularizes",
+  "popularising": "popularizing",
+  "pouffe": "pouf",
+  "pouffes": "poufs",
+  "practise": "practice",
+  "practised": "practiced",
+  "practises": "practices",
+  "practising": "practicing",
+  "praesidium": "presidium",
+  "praesidiums": "presidiums",
+  "pressurisation": "pressurization",
+  "pressurise": "pressurize",
+  "pressurised": "pressurized",
+  "pressurises": "pressurizes",
+  "pressurising": "pressurizing",
+  "pretence": "pretense",
+  "pretences": "pretenses",
+  "primaeval": "primeval",
+  "prioritisation": "prioritization",
+  "prioritise": "prioritize",
+  "prioritised": "prioritized",
+  "prioritises": "prioritizes",
+  "prioritising": "prioritizing",
+  "privatisation": "privatization",
+  "privatisations": "privatizations",
+  "privatise": "privatize",
+  "privatised": "privatized",
+  "privatises": "privatizes",
+  "privatising": "privatizing",
+  "professionalisation": "professionalization",
+  "professionalise": "professionalize",
+  "professionalised": "professionalized",
+  "professionalises": "professionalizes",
+  "professionalising": "professionalizing",
+  "programme": "program",
+  "programmes": "programs",
+  "prologue": "prolog",
+  "prologues": "prologs",
+  "propagandise": "propagandize",
+  "propagandised": "propagandized",
+  "propagandises": "propagandizes",
+  "propagandising": "propagandizing",
+  "proselytise": "proselytize",
+  "proselytised": "proselytized",
+  "proselytiser": "proselytizer",
+  "proselytisers": "proselytizers",
+  "proselytises": "proselytizes",
+  "proselytising": "proselytizing",
+  "psychoanalyse": "psychoanalyze",
+  "psychoanalysed": "psychoanalyzed",
+  "psychoanalyses": "psychoanalyzes",
+  "psychoanalysing": "psychoanalyzing",
+  "publicise": "publicize",
+  "publicised": "publicized",
+  "publicises": "publicizes",
+  "publicising": "publicizing",
+  "pulverisation": "pulverization",
+  "pulverise": "pulverize",
+  "pulverised": "pulverized",
+  "pulverises": "pulverizes",
+  "pulverising": "pulverizing",
+  "pummelled": "pummel",
+  "pummelling": "pummeled",
+  "pyjama": "pajama",
+  "pyjamas": "pajamas",
+  "pzazz": "pizzazz",
+  "quarrelled": "quarreled",
+  "quarrelling": "quarreling",
+  "radicalise": "radicalize",
+  "radicalised": "radicalized",
+  "radicalises": "radicalizes",
+  "radicalising": "radicalizing",
+  "rancour": "rancor",
+  "randomise": "randomize",
+  "randomised": "randomized",
+  "randomises": "randomizes",
+  "randomising": "randomizing",
+  "rationalisation": "rationalization",
+  "rationalisations": "rationalizations",
+  "rationalise": "rationalize",
+  "rationalised": "rationalized",
+  "rationalises": "rationalizes",
+  "rationalising": "rationalizing",
+  "ravelled": "raveled",
+  "ravelling": "raveling",
+  "realisable": "realizable",
+  "realisation": "realization",
+  "realisations": "realizations",
+  "realise": "realize",
+  "realised": "realized",
+  "realises": "realizes",
+  "realising": "realizing",
+  "recognisable": "recognizable",
+  "recognisably": "recognizably",
+  "recognisance": "recognizance",
+  "recognise": "recognize",
+  "recognised": "recognized",
+  "recognises": "recognizes",
+  "recognising": "recognizing",
+  "reconnoitre": "reconnoiter",
+  "reconnoitred": "reconnoitered",
+  "reconnoitres": "reconnoiters",
+  "reconnoitring": "reconnoitering",
+  "refuelled": "refueled",
+  "refuelling": "refueling",
+  "regularisation": "regularization",
+  "regularise": "regularize",
+  "regularised": "regularized",
+  "regularises": "regularizes",
+  "regularising": "regularizing",
+  "remodelled": "remodeled",
+  "remodelling": "remodeling",
+  "remould": "remold",
+  "remoulded": "remolded",
+  "remoulding": "remolding",
+  "remoulds": "remolds",
+  "reorganisation": "reorganization",
+  "reorganisations": "reorganizations",
+  "reorganise": "reorganize",
+  "reorganised": "reorganized",
+  "reorganises": "reorganizes",
+  "reorganising": "reorganizing",
+  "revelled": "reveled",
+  "reveller": "reveler",
+  "revellers": "revelers",
+  "revelling": "reveling",
+  "revitalise": "revitalize",
+  "revitalised": "revitalized",
+  "revitalises": "revitalizes",
+  "revitalising": "revitalizing",
+  "revolutionise": "revolutionize",
+  "revolutionised": "revolutionized",
+  "revolutionises": "revolutionizes",
+  "revolutionising": "revolutionizing",
+  "rhapsodise": "rhapsodize",
+  "rhapsodised": "rhapsodized",
+  "rhapsodises": "rhapsodizes",
+  "rhapsodising": "rhapsodizing",
+  "rigour": "rigor",
+  "rigours": "rigors",
+  "ritualised": "ritualized",
+  "rivalled": "rivaled",
+  "rivalling": "rivaling",
+  "romanticise": "romanticize",
+  "romanticised": "romanticized",
+  "romanticises": "romanticizes",
+  "romanticising": "romanticizing",
+  "rumour": "rumor",
+  "rumoured": "rumored",
+  "rumours": "rumors",
+  "sabre": "saber",
+  "sabres": "sabers",
+  "saltpetre": "saltpeter",
+  "sanitise": "sanitize",
+  "sanitised": "sanitized",
+  "sanitises": "sanitizes",
+  "sanitising": "sanitizing",
+  "satirise": "satirize",
+  "satirised": "satirized",
+  "satirises": "satirizes",
+  "satirising": "satirizing",
+  "saviour": "savior",
+  "saviours": "saviors",
+  "savour": "savor",
+  "savoured": "savored",
+  "savouries": "savories",
+  "savouring": "savoring",
+  "savours": "savors",
+  "savoury": "savory",
+  "scandalise": "scandalize",
+  "scandalised": "scandalized",
+  "scandalises": "scandalizes",
+  "scandalising": "scandalizing",
+  "sceptic": "skeptic",
+  "sceptical": "skeptical",
+  "sceptically": "skeptically",
+  "scepticism": "skepticism",
+  "sceptics": "skeptics",
+  "sceptre": "scepter",
+  "sceptres": "scepters",
+  "scrutinise": "scrutinize",
+  "scrutinised": "scrutinized",
+  "scrutinises": "scrutinizes",
+  "scrutinising": "scrutinizing",
+  "secularisation": "secularization",
+  "secularise": "secularize",
+  "secularised": "secularized",
+  "secularises": "secularizes",
+  "secularising": "secularizing",
+  "sensationalise": "sensationalize",
+  "sensationalised": "sensationalized",
+  "sensationalises": "sensationalizes",
+  "sensationalising": "sensationalizing",
+  "sensitise": "sensitize",
+  "sensitised": "sensitized",
+  "sensitises": "sensitizes",
+  "sensitising": "sensitizing",
+  "sentimentalise": "sentimentalize",
+  "sentimentalised": "sentimentalized",
+  "sentimentalises": "sentimentalizes",
+  "sentimentalising": "sentimentalizing",
+  "sepulchre": "sepulcher",
+  "sepulchres": "sepulchers",
+  "serialisation": "serialization",
+  "serialisations": "serializations",
+  "serialise": "serialize",
+  "serialised": "serialized",
+  "serialises": "serializes",
+  "serialising": "serializing",
+  "sermonise": "sermonize",
+  "sermonised": "sermonized",
+  "sermonises": "sermonizes",
+  "sermonising": "sermonizing",
+  "sheikh": "sheik",
+  "shovelled": "shoveled",
+  "shovelling": "shoveling",
+  "shrivelled": "shriveled",
+  "shrivelling": "shriveling",
+  "signalise": "signalize",
+  "signalised": "signalized",
+  "signalises": "signalizes",
+  "signalising": "signalizing",
+  "signalled": "signaled",
+  "signalling": "signaling",
+  "smoulder": "smolder",
+  "smouldered": "smoldered",
+  "smouldering": "smoldering",
+  "smoulders": "smolders",
+  "snivelled": "sniveled",
+  "snivelling": "sniveling",
+  "snorkelled": "snorkeled",
+  "snorkelling": "snorkeling",
+  "snowplough": "snowplow",
+  "snowploughs": "snowplow",
+  "socialisation": "socialization",
+  "socialise": "socialize",
+  "socialised": "socialized",
+  "socialises": "socializes",
+  "socialising": "socializing",
+  "sodomise": "sodomize",
+  "sodomised": "sodomized",
+  "sodomises": "sodomizes",
+  "sodomising": "sodomizing",
+  "solemnise": "solemnize",
+  "solemnised": "solemnized",
+  "solemnises": "solemnizes",
+  "solemnising": "solemnizing",
+  "sombre": "somber",
+  "specialisation": "specialization",
+  "specialisations": "specializations",
+  "specialise": "specialize",
+  "specialised": "specialized",
+  "specialises": "specializes",
+  "specialising": "specializing",
+  "spectre": "specter",
+  "spectres": "specters",
+  "spiralled": "spiraled",
+  "spiralling": "spiraling",
+  "splendour": "splendor",
+  "splendours": "splendors",
+  "squirrelled": "squirreled",
+  "squirrelling": "squirreling",
+  "stabilisation": "stabilization",
+  "stabilise": "stabilize",
+  "stabilised": "stabilized",
+  "stabiliser": "stabilizer",
+  "stabilisers": "stabilizers",
+  "stabilises": "stabilizes",
+  "stabilising": "stabilizing",
+  "standardisation": "standardization",
+  "standardise": "standardize",
+  "standardised": "standardized",
+  "standardises": "standardizes",
+  "standardising": "standardizing",
+  "stencilled": "stenciled",
+  "stencilling": "stenciling",
+  "sterilisation": "sterilization",
+  "sterilisations": "sterilizations",
+  "sterilise": "sterilize",
+  "sterilised": "sterilized",
+  "steriliser": "sterilizer",
+  "sterilisers": "sterilizers",
+  "sterilises": "sterilizes",
+  "sterilising": "sterilizing",
+  "stigmatisation": "stigmatization",
+  "stigmatise": "stigmatize",
+  "stigmatised": "stigmatized",
+  "stigmatises": "stigmatizes",
+  "stigmatising": "stigmatizing",
+  "storey": "story",
+  "storeys": "stories",
+  "subsidisation": "subsidization",
+  "subsidise": "subsidize",
+  "subsidised": "subsidized",
+  "subsidiser": "subsidizer",
+  "subsidisers": "subsidizers",
+  "subsidises": "subsidizes",
+  "subsidising": "subsidizing",
+  "succour": "succor",
+  "succoured": "succored",
+  "succouring": "succoring",
+  "succours": "succors",
+  "sulphate": "sulfate",
+  "sulphates": "sulfates",
+  "sulphide": "sulfide",
+  "sulphides": "sulfides",
+  "sulphur": "sulfur",
+  "sulphurous": "sulfurous",
+  "summarise": "summarize",
+  "summarised": "summarized",
+  "summarises": "summarizes",
+  "summarising": "summarizing",
+  "swivelled": "swiveled",
+  "swivelling": "swiveling",
+  "symbolise": "symbolize",
+  "symbolised": "symbolized",
+  "symbolises": "symbolizes",
+  "symbolising": "symbolizing",
+  "sympathise": "sympathize",
+  "sympathised": "sympathized",
+  "sympathiser": "sympathizer",
+  "sympathisers": "sympathizers",
+  "sympathises": "sympathizes",
+  "sympathising": "sympathizing",
+  "synchronisation": "synchronization",
+  "synchronise": "synchronize",
+  "synchronised": "synchronized",
+  "synchronises": "synchronizes",
+  "synchronising": "synchronizing",
+  "synthesise": "synthesize",
+  "synthesised": "synthesized",
+  "synthesiser": "synthesizer",
+  "synthesisers": "synthesizers",
+  "synthesises": "synthesizes",
+  "synthesising": "synthesizing",
+  "syphon": "siphon",
+  "syphoned": "siphoned",
+  "syphoning": "siphoning",
+  "syphons": "siphons",
+  "systematisation": "systematization",
+  "systematise": "systematize",
+  "systematised": "systematized",
+  "systematises": "systematizes",
+  "systematising": "systematizing",
+  "tantalise": "tantalize",
+  "tantalised": "tantalized",
+  "tantalises": "tantalizes",
+  "tantalising": "tantalizing",
+  "tantalisingly": "tantalizingly",
+  "tasselled": "tasseled",
+  "technicolour": "technicolor",
+  "temporise": "temporize",
+  "temporised": "temporized",
+  "temporises": "temporizes",
+  "temporising": "temporizing",
+  "tenderise": "tenderize",
+  "tenderised": "tenderized",
+  "tenderises": "tenderizes",
+  "tenderising": "tenderizing",
+  "terrorise": "terrorize",
+  "terrorised": "terrorized",
+  "terrorises": "terrorizes",
+  "terrorising": "terrorizing",
+  "theatre": "theater",
+  "theatregoer": "theatergoer",
+  "theatregoers": "theatergoers",
+  "theatres": "theaters",
+  "theorise": "theorize",
+  "theorised": "theorized",
+  "theorises": "theorizes",
+  "theorising": "theorizing",
+  "tonne": "ton",
+  "tonnes": "tons",
+  "towelled": "toweled",
+  "towelling": "toweling",
+  "toxaemia": "toxemia",
+  "tranquillise": "tranquilize",
+  "tranquillised": "tranquilized",
+  "tranquilliser": "tranquilizer",
+  "tranquillisers": "tranquilizers",
+  "tranquillises": "tranquilizes",
+  "tranquillising": "tranquilizing",
+  "tranquillity": "tranquility",
+  "tranquillize": "tranquilize",
+  "tranquillized": "tranquilized",
+  "tranquillizer": "tranquilizer",
+  "tranquillizers": "tranquilizers",
+  "tranquillizes": "tranquilizes",
+  "tranquillizing": "tranquilizing",
+  "tranquilly": "tranquility",
+  "transistorised": "transistorized",
+  "traumatise": "traumatize",
+  "traumatised": "traumatized",
+  "traumatises": "traumatizes",
+  "traumatising": "traumatizing",
+  "travelled": "traveled",
+  "traveller": "traveler",
+  "travellers": "travelers",
+  "travelling": "traveling",
+  "travelog": "travelogue",
+  "travelogs": "travelogues",
+  "trialled": "trialed",
+  "trialling": "trialing",
+  "tricolour": "tricolor",
+  "tricolours": "tricolors",
+  "trivialise": "trivialize",
+  "trivialised": "trivialized",
+  "trivialises": "trivializes",
+  "trivialising": "trivializing",
+  "tumour": "tumor",
+  "tumours": "tumors",
+  "tunnelled": "tunneled",
+  "tunnelling": "tunneling",
+  "tyrannise": "tyrannize",
+  "tyrannised": "tyrannized",
+  "tyrannises": "tyrannizes",
+  "tyrannising": "tyrannizing",
+  "tyre": "tire",
+  "tyres": "tires",
+  "unauthorised": "unauthorized",
+  "uncivilised": "uncivilized",
+  "underutilised": "underutilized",
+  "unequalled": "unequaled",
+  "unfavourable": "unfavorable",
+  "unfavourably": "unfavorably",
+  "unionisation": "unionization",
+  "unionise": "unionize",
+  "unionised": "unionized",
+  "unionises": "unionizes",
+  "unionising": "unionizing",
+  "unorganised": "unorganized",
+  "unravelled": "unraveled",
+  "unravelling": "unraveling",
+  "unrecognisable": "unrecognizable",
+  "unrecognised": "unrecognized",
+  "unrivalled": "unrivaled",
+  "unsavoury": "unsavory",
+  "untrammelled": "untrammeled",
+  "urbanisation": "urbanization",
+  "urbanise": "urbanize",
+  "urbanised": "urbanized",
+  "urbanises": "urbanizes",
+  "urbanising": "urbanizing",
+  "utilisable": "utilizable",
+  "utilisation": "utilization",
+  "utilise": "utilize",
+  "utilised": "utilized",
+  "utilises": "utilizes",
+  "utilising": "utilizing",
+  "valour": "valor",
+  "vandalise": "vandalize",
+  "vandalised": "vandalized",
+  "vandalises": "vandalizes",
+  "vandalising": "vandalizing",
+  "vaporisation": "vaporization",
+  "vaporise": "vaporize",
+  "vaporised": "vaporized",
+  "vaporises": "vaporizes",
+  "vaporising": "vaporizing",
+  "vapour": "vapor",
+  "vapours": "vapors",
+  "verbalise": "verbalize",
+  "verbalised": "verbalized",
+  "verbalises": "verbalizes",
+  "verbalising": "verbalizing",
+  "victimisation": "victimization",
+  "victimise": "victimize",
+  "victimised": "victimized",
+  "victimises": "victimizes",
+  "victimising": "victimizing",
+  "videodisc": "videodisk",
+  "videodiscs": "videodisks",
+  "vigour": "vigor",
+  "visualisation": "visualization",
+  "visualisations": "visualizations",
+  "visualise": "visualize",
+  "visualised": "visualized",
+  "visualises": "visualizes",
+  "visualising": "visualizing",
+  "vocalisation": "vocalization",
+  "vocalisations": "vocalizations",
+  "vocalise": "vocalize",
+  "vocalised": "vocalized",
+  "vocalises": "vocalizes",
+  "vocalising": "vocalizing",
+  "vulcanised": "vulcanized",
+  "vulgarisation": "vulgarization",
+  "vulgarise": "vulgarize",
+  "vulgarised": "vulgarized",
+  "vulgarises": "vulgarizes",
+  "vulgarising": "vulgarizing",
+  "waggon": "wagon",
+  "waggons": "wagons",
+  "watercolour": "watercolor",
+  "watercolours": "watercolors",
+  "weaselled": "weaseled",
+  "weaselling": "weaseling",
+  "westernisation": "westernization",
+  "westernise": "westernize",
+  "westernised": "westernized",
+  "westernises": "westernizes",
+  "westernising": "westernizing",
+  "womanise": "womanize",
+  "womanised": "womanized",
+  "womaniser": "womanizer",
+  "womanisers": "womanizers",
+  "womanises": "womanizes",
+  "womanising": "womanizing",
+  "woollen": "woolen",
+  "woollens": "woolens",
+  "woollies": "woolies",
+  "woolly": "wooly",
+  "worshipped": "worshiped",
+  "worshipper": "worshiper",
+  "worshipping": "worshiping",
+  "yodelled": "yodeled",
+  "yodelling": "yodeling",
+  "yoghourt": "yogurt",
+  "yoghourts": "yogurts",
+  "yoghurt": "yogurt",
+  "yoghurts": "yogurts"
+}

audio_model_states/whisper-small-cantonese/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d3d75f188b0e83816ddfe2c081aa5811fef9f12f90bcf95efbb6f22d4cb03a
+size 1925064044

audio_model_states/whisper-small-cantonese/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

audio_model_states/whisper-small-cantonese/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9563aaf2c8c73c9368146c47fb8767f7b2fc4ec19fa3d2f43de391939240e744
+size 967102601

audio_model_states/whisper-small-cantonese/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5debd200034ecb7c5a4f41ef2227951c0f473e8fae7113e0066142d213a47d2d
+size 14244

audio_model_states/whisper-small-cantonese/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b691e5fdc050ffec60fabc6f70ec25a5c9c5a415de9ceda0c71eee2c5823fe64
+size 557

audio_model_states/whisper-small-cantonese/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554d2698384ad39f5da6b204240a25383b7dfb17d0add781017660bb036bc2f3
+size 1064

audio_model_states/whisper-small-cantonese/special_tokens_map.json

@@ -0,0 +1,139 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|iw|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

audio_model_states/whisper-small-cantonese/tokenizer_config.json

@@ -0,0 +1,981 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|startoftranscript|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|en|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|zh|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50261": {
+      "content": "<|de|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50262": {
+      "content": "<|es|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50263": {
+      "content": "<|ru|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<|ko|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<|fr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "<|ja|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50267": {
+      "content": "<|pt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50268": {
+      "content": "<|tr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50269": {
+      "content": "<|pl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50270": {
+      "content": "<|ca|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50271": {
+      "content": "<|nl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50272": {
+      "content": "<|ar|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50273": {
+      "content": "<|sv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50274": {
+      "content": "<|it|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50275": {
+      "content": "<|id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50276": {
+      "content": "<|hi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50277": {
+      "content": "<|fi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|vi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<|iw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<|uk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "<|el|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "<|ms|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "<|cs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "<|ro|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "<|da|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50286": {
+      "content": "<|hu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50287": {
+      "content": "<|ta|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50288": {
+      "content": "<|no|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50289": {
+      "content": "<|th|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50290": {
+      "content": "<|ur|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50291": {
+      "content": "<|hr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50292": {
+      "content": "<|bg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50293": {
+      "content": "<|lt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50294": {
+      "content": "<|la|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50295": {
+      "content": "<|mi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50296": {
+      "content": "<|ml|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50297": {
+      "content": "<|cy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50298": {
+      "content": "<|sk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50299": {
+      "content": "<|te|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50300": {
+      "content": "<|fa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50301": {
+      "content": "<|lv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50302": {
+      "content": "<|bn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50303": {
+      "content": "<|sr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50304": {
+      "content": "<|az|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50305": {
+      "content": "<|sl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50306": {
+      "content": "<|kn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50307": {
+      "content": "<|et|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50308": {
+      "content": "<|mk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50309": {
+      "content": "<|br|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50310": {
+      "content": "<|eu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50311": {
+      "content": "<|is|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50312": {
+      "content": "<|hy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50313": {
+      "content": "<|ne|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50314": {
+      "content": "<|mn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50315": {
+      "content": "<|bs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50316": {
+      "content": "<|kk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50317": {
+      "content": "<|sq|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50318": {
+      "content": "<|sw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50319": {
+      "content": "<|gl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50320": {
+      "content": "<|mr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50321": {
+      "content": "<|pa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50322": {
+      "content": "<|si|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50323": {
+      "content": "<|km|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50324": {
+      "content": "<|sn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50325": {
+      "content": "<|yo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50326": {
+      "content": "<|so|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50327": {
+      "content": "<|af|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50328": {
+      "content": "<|oc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50329": {
+      "content": "<|ka|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50330": {
+      "content": "<|be|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50331": {
+      "content": "<|tg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50332": {
+      "content": "<|sd|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50333": {
+      "content": "<|gu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50334": {
+      "content": "<|am|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50335": {
+      "content": "<|yi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50336": {
+      "content": "<|lo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50337": {
+      "content": "<|uz|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50338": {
+      "content": "<|fo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50339": {
+      "content": "<|ht|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50340": {
+      "content": "<|ps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50341": {
+      "content": "<|tk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50342": {
+      "content": "<|nn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50343": {
+      "content": "<|mt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50344": {
+      "content": "<|sa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50345": {
+      "content": "<|lb|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50346": {
+      "content": "<|my|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50347": {
+      "content": "<|bo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50348": {
+      "content": "<|tl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50349": {
+      "content": "<|mg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50350": {
+      "content": "<|as|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50351": {
+      "content": "<|tt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50352": {
+      "content": "<|haw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50353": {
+      "content": "<|ln|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50354": {
+      "content": "<|ha|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50355": {
+      "content": "<|ba|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50356": {
+      "content": "<|jw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50357": {
+      "content": "<|su|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50358": {
+      "content": "<|translate|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50359": {
+      "content": "<|transcribe|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50360": {
+      "content": "<|startoflm|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50361": {
+      "content": "<|startofprev|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50362": {
+      "content": "<|nocaptions|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50363": {
+      "content": "<|notimestamps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|iw|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": ""
+}

audio_model_states/whisper-small-cantonese/trainer_state.json

@@ -0,0 +1,3891 @@
+{
+  "best_metric": 10.695329087048833,
+  "best_model_checkpoint": "./model_out/checkpoint-10000",
+  "epoch": 5.5514433752775725,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.2092,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.8939,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.4e-06,
+      "loss": 0.7337,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 0.6496,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.24e-05,
+      "loss": 0.5998,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.49e-05,
+      "loss": 0.5262,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.74e-05,
+      "loss": 0.501,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 0.4801,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.2400000000000002e-05,
+      "loss": 0.4495,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4900000000000002e-05,
+      "loss": 0.4372,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7300000000000003e-05,
+      "loss": 0.425,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.98e-05,
+      "loss": 0.4097,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2300000000000006e-05,
+      "loss": 0.3997,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.48e-05,
+      "loss": 0.3828,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.73e-05,
+      "loss": 0.3817,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.9800000000000005e-05,
+      "loss": 0.3696,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.23e-05,
+      "loss": 0.3808,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.4800000000000005e-05,
+      "loss": 0.3764,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.73e-05,
+      "loss": 0.3712,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 0.3416,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "eval_cer": 13.553988474370641,
+      "eval_loss": 0.2625325620174408,
+      "eval_runtime": 367.6787,
+      "eval_samples_per_second": 7.02,
+      "eval_steps_per_second": 0.878,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.992068965517242e-05,
+      "loss": 0.3682,
+      "step": 525
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.9834482758620695e-05,
+      "loss": 0.3716,
+      "step": 550
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9748275862068966e-05,
+      "loss": 0.3581,
+      "step": 575
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.966206896551724e-05,
+      "loss": 0.3542,
+      "step": 600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9575862068965514e-05,
+      "loss": 0.347,
+      "step": 625
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.94896551724138e-05,
+      "loss": 0.3603,
+      "step": 650
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.940344827586207e-05,
+      "loss": 0.3568,
+      "step": 675
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.931724137931035e-05,
+      "loss": 0.3408,
+      "step": 700
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9231034482758625e-05,
+      "loss": 0.346,
+      "step": 725
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.9144827586206896e-05,
+      "loss": 0.3382,
+      "step": 750
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.9058620689655174e-05,
+      "loss": 0.3422,
+      "step": 775
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.897241379310345e-05,
+      "loss": 0.3423,
+      "step": 800
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.888620689655173e-05,
+      "loss": 0.3245,
+      "step": 825
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.88e-05,
+      "loss": 0.3378,
+      "step": 850
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.871379310344828e-05,
+      "loss": 0.3388,
+      "step": 875
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.8627586206896556e-05,
+      "loss": 0.3189,
+      "step": 900
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.8541379310344834e-05,
+      "loss": 0.3264,
+      "step": 925
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.8455172413793105e-05,
+      "loss": 0.3231,
+      "step": 950
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.836896551724138e-05,
+      "loss": 0.3046,
+      "step": 975
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.828275862068965e-05,
+      "loss": 0.3115,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "eval_cer": 12.473460721868365,
+      "eval_loss": 0.2618062496185303,
+      "eval_runtime": 363.8751,
+      "eval_samples_per_second": 7.093,
+      "eval_steps_per_second": 0.888,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.819655172413793e-05,
+      "loss": 0.3251,
+      "step": 1025
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.811034482758621e-05,
+      "loss": 0.3158,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.8024137931034486e-05,
+      "loss": 0.3093,
+      "step": 1075
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.7937931034482764e-05,
+      "loss": 0.3238,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.7851724137931035e-05,
+      "loss": 0.3128,
+      "step": 1125
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.776551724137931e-05,
+      "loss": 0.3012,
+      "step": 1150
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.767931034482759e-05,
+      "loss": 0.3103,
+      "step": 1175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.759310344827587e-05,
+      "loss": 0.314,
+      "step": 1200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.750689655172414e-05,
+      "loss": 0.325,
+      "step": 1225
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.742068965517242e-05,
+      "loss": 0.2923,
+      "step": 1250
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.733448275862069e-05,
+      "loss": 0.3047,
+      "step": 1275
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.7251724137931034e-05,
+      "loss": 0.3007,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.716551724137931e-05,
+      "loss": 0.3233,
+      "step": 1325
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.707931034482759e-05,
+      "loss": 0.2983,
+      "step": 1350
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.699310344827587e-05,
+      "loss": 0.2961,
+      "step": 1375
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.690689655172414e-05,
+      "loss": 0.2929,
+      "step": 1400
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.6820689655172416e-05,
+      "loss": 0.2839,
+      "step": 1425
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.673448275862069e-05,
+      "loss": 0.2973,
+      "step": 1450
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.664827586206897e-05,
+      "loss": 0.2896,
+      "step": 1475
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.656206896551724e-05,
+      "loss": 0.289,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "eval_cer": 11.809978768577494,
+      "eval_loss": 0.2488066703081131,
+      "eval_runtime": 362.9261,
+      "eval_samples_per_second": 7.112,
+      "eval_steps_per_second": 0.89,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.647586206896552e-05,
+      "loss": 0.2872,
+      "step": 1525
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.638965517241379e-05,
+      "loss": 0.2965,
+      "step": 1550
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.630344827586207e-05,
+      "loss": 0.3036,
+      "step": 1575
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.621724137931035e-05,
+      "loss": 0.2891,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.6131034482758624e-05,
+      "loss": 0.2896,
+      "step": 1625
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.60448275862069e-05,
+      "loss": 0.2992,
+      "step": 1650
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.595862068965517e-05,
+      "loss": 0.2865,
+      "step": 1675
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.587241379310345e-05,
+      "loss": 0.3007,
+      "step": 1700
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.578620689655173e-05,
+      "loss": 0.3108,
+      "step": 1725
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.5700000000000006e-05,
+      "loss": 0.2861,
+      "step": 1750
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.561379310344828e-05,
+      "loss": 0.2996,
+      "step": 1775
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.5527586206896555e-05,
+      "loss": 0.295,
+      "step": 1800
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.5441379310344826e-05,
+      "loss": 0.2848,
+      "step": 1825
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.5355172413793104e-05,
+      "loss": 0.2997,
+      "step": 1850
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.526896551724138e-05,
+      "loss": 0.2828,
+      "step": 1875
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.518620689655173e-05,
+      "loss": 0.2889,
+      "step": 1900
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.5100000000000005e-05,
+      "loss": 0.2893,
+      "step": 1925
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.5013793103448276e-05,
+      "loss": 0.276,
+      "step": 1950
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.4927586206896554e-05,
+      "loss": 0.2784,
+      "step": 1975
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.4841379310344825e-05,
+      "loss": 0.2826,
+      "step": 2000
+    },
+    {
+      "epoch": 0.74,
+      "eval_cer": 13.197603882317258,
+      "eval_loss": 0.2393285036087036,
+      "eval_runtime": 368.8043,
+      "eval_samples_per_second": 6.998,
+      "eval_steps_per_second": 0.876,
+      "step": 2000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.475517241379311e-05,
+      "loss": 0.2707,
+      "step": 2025
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.466896551724138e-05,
+      "loss": 0.2824,
+      "step": 2050
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.458275862068966e-05,
+      "loss": 0.296,
+      "step": 2075
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.4496551724137936e-05,
+      "loss": 0.2786,
+      "step": 2100
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.441034482758621e-05,
+      "loss": 0.2802,
+      "step": 2125
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.4324137931034485e-05,
+      "loss": 0.2791,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.423793103448276e-05,
+      "loss": 0.2953,
+      "step": 2175
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.415172413793104e-05,
+      "loss": 0.2807,
+      "step": 2200
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.406551724137931e-05,
+      "loss": 0.2776,
+      "step": 2225
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.397931034482759e-05,
+      "loss": 0.2798,
+      "step": 2250
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.389310344827586e-05,
+      "loss": 0.2804,
+      "step": 2275
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.3806896551724144e-05,
+      "loss": 0.2892,
+      "step": 2300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.3720689655172415e-05,
+      "loss": 0.2773,
+      "step": 2325
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.363448275862069e-05,
+      "loss": 0.2733,
+      "step": 2350
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.3548275862068964e-05,
+      "loss": 0.2805,
+      "step": 2375
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.346206896551724e-05,
+      "loss": 0.274,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.337586206896552e-05,
+      "loss": 0.2711,
+      "step": 2425
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.32896551724138e-05,
+      "loss": 0.2684,
+      "step": 2450
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.320344827586207e-05,
+      "loss": 0.2731,
+      "step": 2475
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.3117241379310346e-05,
+      "loss": 0.2689,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "eval_cer": 13.10282074613285,
+      "eval_loss": 0.24490514397621155,
+      "eval_runtime": 366.5991,
+      "eval_samples_per_second": 7.04,
+      "eval_steps_per_second": 0.881,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.3031034482758624e-05,
+      "loss": 0.2702,
+      "step": 2525
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.29448275862069e-05,
+      "loss": 0.2623,
+      "step": 2550
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.285862068965518e-05,
+      "loss": 0.2749,
+      "step": 2575
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.277241379310345e-05,
+      "loss": 0.2658,
+      "step": 2600
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.268620689655173e-05,
+      "loss": 0.2637,
+      "step": 2625
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.26e-05,
+      "loss": 0.2823,
+      "step": 2650
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.2513793103448276e-05,
+      "loss": 0.2641,
+      "step": 2675
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.2427586206896554e-05,
+      "loss": 0.2721,
+      "step": 2700
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.234137931034483e-05,
+      "loss": 0.1882,
+      "step": 2725
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.22551724137931e-05,
+      "loss": 0.1776,
+      "step": 2750
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.216896551724138e-05,
+      "loss": 0.1768,
+      "step": 2775
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.208275862068966e-05,
+      "loss": 0.1714,
+      "step": 2800
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.1996551724137936e-05,
+      "loss": 0.1771,
+      "step": 2825
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.191034482758621e-05,
+      "loss": 0.193,
+      "step": 2850
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.1824137931034485e-05,
+      "loss": 0.1788,
+      "step": 2875
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.1737931034482756e-05,
+      "loss": 0.1784,
+      "step": 2900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.1651724137931034e-05,
+      "loss": 0.1879,
+      "step": 2925
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.156551724137932e-05,
+      "loss": 0.1825,
+      "step": 2950
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.147931034482759e-05,
+      "loss": 0.1854,
+      "step": 2975
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.139310344827587e-05,
+      "loss": 0.1882,
+      "step": 3000
+    },
+    {
+      "epoch": 1.11,
+      "eval_cer": 11.67728237791932,
+      "eval_loss": 0.25736209750175476,
+      "eval_runtime": 361.0573,
+      "eval_samples_per_second": 7.148,
+      "eval_steps_per_second": 0.895,
+      "step": 3000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.130689655172414e-05,
+      "loss": 0.1827,
+      "step": 3025
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.1220689655172415e-05,
+      "loss": 0.1889,
+      "step": 3050
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.113448275862069e-05,
+      "loss": 0.1938,
+      "step": 3075
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.104827586206897e-05,
+      "loss": 0.182,
+      "step": 3100
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 4.096206896551724e-05,
+      "loss": 0.1884,
+      "step": 3125
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.087586206896552e-05,
+      "loss": 0.182,
+      "step": 3150
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.078965517241379e-05,
+      "loss": 0.1795,
+      "step": 3175
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.070344827586207e-05,
+      "loss": 0.176,
+      "step": 3200
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 4.0617241379310346e-05,
+      "loss": 0.1834,
+      "step": 3225
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.0531034482758624e-05,
+      "loss": 0.1886,
+      "step": 3250
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 4.0444827586206895e-05,
+      "loss": 0.1908,
+      "step": 3275
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.035862068965517e-05,
+      "loss": 0.1813,
+      "step": 3300
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.027241379310345e-05,
+      "loss": 0.1875,
+      "step": 3325
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.018620689655173e-05,
+      "loss": 0.1925,
+      "step": 3350
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.0100000000000006e-05,
+      "loss": 0.1855,
+      "step": 3375
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.001379310344828e-05,
+      "loss": 0.194,
+      "step": 3400
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.9927586206896554e-05,
+      "loss": 0.1827,
+      "step": 3425
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.9841379310344825e-05,
+      "loss": 0.1806,
+      "step": 3450
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.975517241379311e-05,
+      "loss": 0.1783,
+      "step": 3475
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.966896551724138e-05,
+      "loss": 0.1889,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "eval_cer": 11.434637549287231,
+      "eval_loss": 0.24476666748523712,
+      "eval_runtime": 361.1188,
+      "eval_samples_per_second": 7.147,
+      "eval_steps_per_second": 0.894,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.958275862068966e-05,
+      "loss": 0.185,
+      "step": 3525
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.949655172413793e-05,
+      "loss": 0.1833,
+      "step": 3550
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.941034482758621e-05,
+      "loss": 0.1749,
+      "step": 3575
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.9324137931034485e-05,
+      "loss": 0.1906,
+      "step": 3600
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.923793103448276e-05,
+      "loss": 0.1934,
+      "step": 3625
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.9151724137931034e-05,
+      "loss": 0.1782,
+      "step": 3650
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.906551724137931e-05,
+      "loss": 0.19,
+      "step": 3675
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 3.897931034482758e-05,
+      "loss": 0.1943,
+      "step": 3700
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 3.889310344827587e-05,
+      "loss": 0.1838,
+      "step": 3725
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.8806896551724145e-05,
+      "loss": 0.2248,
+      "step": 3750
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.8720689655172416e-05,
+      "loss": 0.1853,
+      "step": 3775
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.863448275862069e-05,
+      "loss": 0.1867,
+      "step": 3800
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.8548275862068964e-05,
+      "loss": 0.1801,
+      "step": 3825
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.846206896551724e-05,
+      "loss": 0.182,
+      "step": 3850
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.837586206896552e-05,
+      "loss": 0.1843,
+      "step": 3875
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.82896551724138e-05,
+      "loss": 0.184,
+      "step": 3900
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.820344827586207e-05,
+      "loss": 0.1808,
+      "step": 3925
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.8117241379310346e-05,
+      "loss": 0.188,
+      "step": 3950
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.8031034482758624e-05,
+      "loss": 0.1691,
+      "step": 3975
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.79448275862069e-05,
+      "loss": 0.1923,
+      "step": 4000
+    },
+    {
+      "epoch": 1.48,
+      "eval_cer": 11.8895966029724,
+      "eval_loss": 0.24924282729625702,
+      "eval_runtime": 360.2098,
+      "eval_samples_per_second": 7.165,
+      "eval_steps_per_second": 0.897,
+      "step": 4000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.785862068965517e-05,
+      "loss": 0.175,
+      "step": 4025
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.777241379310345e-05,
+      "loss": 0.1814,
+      "step": 4050
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.768620689655172e-05,
+      "loss": 0.1808,
+      "step": 4075
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 3.76e-05,
+      "loss": 0.1875,
+      "step": 4100
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.7513793103448284e-05,
+      "loss": 0.1831,
+      "step": 4125
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 3.7427586206896555e-05,
+      "loss": 0.184,
+      "step": 4150
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.734137931034483e-05,
+      "loss": 0.1774,
+      "step": 4175
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.72551724137931e-05,
+      "loss": 0.1716,
+      "step": 4200
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.716896551724138e-05,
+      "loss": 0.1845,
+      "step": 4225
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 3.708275862068966e-05,
+      "loss": 0.1854,
+      "step": 4250
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.6996551724137937e-05,
+      "loss": 0.1824,
+      "step": 4275
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 3.691034482758621e-05,
+      "loss": 0.1796,
+      "step": 4300
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.6824137931034485e-05,
+      "loss": 0.1882,
+      "step": 4325
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.6737931034482756e-05,
+      "loss": 0.1866,
+      "step": 4350
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.6651724137931034e-05,
+      "loss": 0.1881,
+      "step": 4375
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.656551724137931e-05,
+      "loss": 0.1822,
+      "step": 4400
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.647931034482759e-05,
+      "loss": 0.1803,
+      "step": 4425
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.639310344827586e-05,
+      "loss": 0.1851,
+      "step": 4450
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.630689655172414e-05,
+      "loss": 0.1825,
+      "step": 4475
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.6220689655172416e-05,
+      "loss": 0.1886,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "eval_cer": 11.75310888686685,
+      "eval_loss": 0.23957248032093048,
+      "eval_runtime": 361.2575,
+      "eval_samples_per_second": 7.144,
+      "eval_steps_per_second": 0.894,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.6134482758620694e-05,
+      "loss": 0.1944,
+      "step": 4525
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.604827586206897e-05,
+      "loss": 0.1896,
+      "step": 4550
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.596206896551724e-05,
+      "loss": 0.1819,
+      "step": 4575
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.587586206896552e-05,
+      "loss": 0.1892,
+      "step": 4600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.578965517241379e-05,
+      "loss": 0.1914,
+      "step": 4625
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.5703448275862076e-05,
+      "loss": 0.181,
+      "step": 4650
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.5617241379310346e-05,
+      "loss": 0.1799,
+      "step": 4675
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.5531034482758624e-05,
+      "loss": 0.1784,
+      "step": 4700
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.5444827586206895e-05,
+      "loss": 0.1812,
+      "step": 4725
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.535862068965517e-05,
+      "loss": 0.1782,
+      "step": 4750
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.527241379310345e-05,
+      "loss": 0.1783,
+      "step": 4775
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.518620689655173e-05,
+      "loss": 0.2002,
+      "step": 4800
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.51e-05,
+      "loss": 0.1948,
+      "step": 4825
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.501379310344828e-05,
+      "loss": 0.1791,
+      "step": 4850
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.492758620689655e-05,
+      "loss": 0.2018,
+      "step": 4875
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.484137931034483e-05,
+      "loss": 0.1828,
+      "step": 4900
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.475517241379311e-05,
+      "loss": 0.1834,
+      "step": 4925
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.466896551724138e-05,
+      "loss": 0.1821,
+      "step": 4950
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.458275862068966e-05,
+      "loss": 0.1864,
+      "step": 4975
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.449655172413793e-05,
+      "loss": 0.1899,
+      "step": 5000
+    },
+    {
+      "epoch": 1.85,
+      "eval_cer": 12.048832271762208,
+      "eval_loss": 0.23497651517391205,
+      "eval_runtime": 363.6465,
+      "eval_samples_per_second": 7.098,
+      "eval_steps_per_second": 0.888,
+      "step": 5000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.441034482758621e-05,
+      "loss": 0.1805,
+      "step": 5025
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.4324137931034485e-05,
+      "loss": 0.1826,
+      "step": 5050
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.423793103448276e-05,
+      "loss": 0.1863,
+      "step": 5075
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.4151724137931034e-05,
+      "loss": 0.1754,
+      "step": 5100
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.406551724137931e-05,
+      "loss": 0.1801,
+      "step": 5125
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 3.397931034482758e-05,
+      "loss": 0.1846,
+      "step": 5150
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.389310344827587e-05,
+      "loss": 0.1717,
+      "step": 5175
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.380689655172414e-05,
+      "loss": 0.1754,
+      "step": 5200
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.3720689655172416e-05,
+      "loss": 0.1819,
+      "step": 5225
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.363448275862069e-05,
+      "loss": 0.1792,
+      "step": 5250
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.3548275862068965e-05,
+      "loss": 0.1837,
+      "step": 5275
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.346206896551724e-05,
+      "loss": 0.188,
+      "step": 5300
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.337586206896552e-05,
+      "loss": 0.1875,
+      "step": 5325
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.32896551724138e-05,
+      "loss": 0.1909,
+      "step": 5350
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.320344827586207e-05,
+      "loss": 0.1714,
+      "step": 5375
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.311724137931035e-05,
+      "loss": 0.1921,
+      "step": 5400
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 3.3031034482758624e-05,
+      "loss": 0.1109,
+      "step": 5425
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 3.29448275862069e-05,
+      "loss": 0.0946,
+      "step": 5450
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 3.285862068965517e-05,
+      "loss": 0.0967,
+      "step": 5475
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 3.277241379310345e-05,
+      "loss": 0.1009,
+      "step": 5500
+    },
+    {
+      "epoch": 2.04,
+      "eval_cer": 11.404306945708221,
+      "eval_loss": 0.24928008019924164,
+      "eval_runtime": 359.254,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 0.899,
+      "step": 5500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 3.268620689655172e-05,
+      "loss": 0.0954,
+      "step": 5525
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 3.26e-05,
+      "loss": 0.0999,
+      "step": 5550
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 3.251379310344828e-05,
+      "loss": 0.0946,
+      "step": 5575
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 3.2427586206896555e-05,
+      "loss": 0.0949,
+      "step": 5600
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 3.2341379310344826e-05,
+      "loss": 0.1032,
+      "step": 5625
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 3.2255172413793104e-05,
+      "loss": 0.1002,
+      "step": 5650
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 3.216896551724138e-05,
+      "loss": 0.0973,
+      "step": 5675
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 3.208275862068966e-05,
+      "loss": 0.0984,
+      "step": 5700
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.199655172413794e-05,
+      "loss": 0.1031,
+      "step": 5725
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.191034482758621e-05,
+      "loss": 0.0968,
+      "step": 5750
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.1824137931034486e-05,
+      "loss": 0.0983,
+      "step": 5775
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.173793103448276e-05,
+      "loss": 0.1088,
+      "step": 5800
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.165172413793104e-05,
+      "loss": 0.0998,
+      "step": 5825
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.156551724137931e-05,
+      "loss": 0.0991,
+      "step": 5850
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.147931034482759e-05,
+      "loss": 0.103,
+      "step": 5875
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.139310344827586e-05,
+      "loss": 0.1046,
+      "step": 5900
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.130689655172414e-05,
+      "loss": 0.099,
+      "step": 5925
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.1220689655172416e-05,
+      "loss": 0.1002,
+      "step": 5950
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.1134482758620694e-05,
+      "loss": 0.1028,
+      "step": 5975
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.1048275862068965e-05,
+      "loss": 0.1003,
+      "step": 6000
+    },
+    {
+      "epoch": 2.22,
+      "eval_cer": 11.373976342129207,
+      "eval_loss": 0.2572503387928009,
+      "eval_runtime": 359.7119,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 0.898,
+      "step": 6000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.096206896551724e-05,
+      "loss": 0.0954,
+      "step": 6025
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.0875862068965514e-05,
+      "loss": 0.0981,
+      "step": 6050
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.07896551724138e-05,
+      "loss": 0.1006,
+      "step": 6075
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.070344827586207e-05,
+      "loss": 0.1005,
+      "step": 6100
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.061724137931035e-05,
+      "loss": 0.1007,
+      "step": 6125
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.0531034482758625e-05,
+      "loss": 0.1005,
+      "step": 6150
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.04448275862069e-05,
+      "loss": 0.0968,
+      "step": 6175
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.0358620689655177e-05,
+      "loss": 0.1034,
+      "step": 6200
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 3.0272413793103448e-05,
+      "loss": 0.0982,
+      "step": 6225
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.018620689655173e-05,
+      "loss": 0.1033,
+      "step": 6250
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 3.01e-05,
+      "loss": 0.1031,
+      "step": 6275
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.0013793103448278e-05,
+      "loss": 0.0985,
+      "step": 6300
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.9931034482758624e-05,
+      "loss": 0.1405,
+      "step": 6325
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.9844827586206898e-05,
+      "loss": 0.1059,
+      "step": 6350
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.9758620689655176e-05,
+      "loss": 0.098,
+      "step": 6375
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.967241379310345e-05,
+      "loss": 0.1029,
+      "step": 6400
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.9586206896551728e-05,
+      "loss": 0.1082,
+      "step": 6425
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.95e-05,
+      "loss": 0.1049,
+      "step": 6450
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.941379310344828e-05,
+      "loss": 0.0996,
+      "step": 6475
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.932758620689655e-05,
+      "loss": 0.1031,
+      "step": 6500
+    },
+    {
+      "epoch": 2.41,
+      "eval_cer": 12.954959053685169,
+      "eval_loss": 0.26603972911834717,
+      "eval_runtime": 369.9518,
+      "eval_samples_per_second": 6.977,
+      "eval_steps_per_second": 0.873,
+      "step": 6500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.924137931034483e-05,
+      "loss": 0.1062,
+      "step": 6525
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.9155172413793103e-05,
+      "loss": 0.1057,
+      "step": 6550
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.906896551724138e-05,
+      "loss": 0.1063,
+      "step": 6575
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.8982758620689655e-05,
+      "loss": 0.1064,
+      "step": 6600
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.8896551724137933e-05,
+      "loss": 0.1026,
+      "step": 6625
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.881034482758621e-05,
+      "loss": 0.1068,
+      "step": 6650
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.8724137931034485e-05,
+      "loss": 0.1008,
+      "step": 6675
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2.8637931034482763e-05,
+      "loss": 0.1118,
+      "step": 6700
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 2.8551724137931034e-05,
+      "loss": 0.1017,
+      "step": 6725
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.8465517241379315e-05,
+      "loss": 0.1059,
+      "step": 6750
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 2.8379310344827586e-05,
+      "loss": 0.1071,
+      "step": 6775
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 2.8293103448275863e-05,
+      "loss": 0.1057,
+      "step": 6800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.8206896551724138e-05,
+      "loss": 0.1067,
+      "step": 6825
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 2.8120689655172415e-05,
+      "loss": 0.1068,
+      "step": 6850
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 2.803448275862069e-05,
+      "loss": 0.1175,
+      "step": 6875
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.7948275862068968e-05,
+      "loss": 0.0992,
+      "step": 6900
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.7862068965517242e-05,
+      "loss": 0.1085,
+      "step": 6925
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.777586206896552e-05,
+      "loss": 0.1066,
+      "step": 6950
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.768965517241379e-05,
+      "loss": 0.1013,
+      "step": 6975
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.7603448275862072e-05,
+      "loss": 0.1048,
+      "step": 7000
+    },
+    {
+      "epoch": 2.59,
+      "eval_cer": 12.026084319077949,
+      "eval_loss": 0.25693368911743164,
+      "eval_runtime": 363.146,
+      "eval_samples_per_second": 7.107,
+      "eval_steps_per_second": 0.889,
+      "step": 7000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.7517241379310343e-05,
+      "loss": 0.1017,
+      "step": 7025
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.743103448275862e-05,
+      "loss": 0.1024,
+      "step": 7050
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.73448275862069e-05,
+      "loss": 0.108,
+      "step": 7075
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.7258620689655173e-05,
+      "loss": 0.0979,
+      "step": 7100
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.717241379310345e-05,
+      "loss": 0.1076,
+      "step": 7125
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.7086206896551725e-05,
+      "loss": 0.1024,
+      "step": 7150
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.1037,
+      "step": 7175
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.6913793103448277e-05,
+      "loss": 0.1063,
+      "step": 7200
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.6827586206896554e-05,
+      "loss": 0.1006,
+      "step": 7225
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.674137931034483e-05,
+      "loss": 0.1093,
+      "step": 7250
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.6655172413793107e-05,
+      "loss": 0.1057,
+      "step": 7275
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.6568965517241378e-05,
+      "loss": 0.1015,
+      "step": 7300
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.648275862068966e-05,
+      "loss": 0.1057,
+      "step": 7325
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.639655172413793e-05,
+      "loss": 0.1067,
+      "step": 7350
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.6310344827586207e-05,
+      "loss": 0.104,
+      "step": 7375
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.6224137931034482e-05,
+      "loss": 0.1035,
+      "step": 7400
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.613793103448276e-05,
+      "loss": 0.1054,
+      "step": 7425
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.6051724137931037e-05,
+      "loss": 0.1083,
+      "step": 7450
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.596551724137931e-05,
+      "loss": 0.1081,
+      "step": 7475
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.587931034482759e-05,
+      "loss": 0.1056,
+      "step": 7500
+    },
+    {
+      "epoch": 2.78,
+      "eval_cer": 11.631786472550804,
+      "eval_loss": 0.26435503363609314,
+      "eval_runtime": 358.991,
+      "eval_samples_per_second": 7.19,
+      "eval_steps_per_second": 0.9,
+      "step": 7500
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.5793103448275864e-05,
+      "loss": 0.103,
+      "step": 7525
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.570689655172414e-05,
+      "loss": 0.1068,
+      "step": 7550
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.5620689655172416e-05,
+      "loss": 0.1,
+      "step": 7575
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.5534482758620693e-05,
+      "loss": 0.101,
+      "step": 7600
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.5448275862068964e-05,
+      "loss": 0.1086,
+      "step": 7625
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.5362068965517246e-05,
+      "loss": 0.1039,
+      "step": 7650
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.5275862068965516e-05,
+      "loss": 0.1007,
+      "step": 7675
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.5189655172413794e-05,
+      "loss": 0.1029,
+      "step": 7700
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.510344827586207e-05,
+      "loss": 0.0989,
+      "step": 7725
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.5017241379310346e-05,
+      "loss": 0.1042,
+      "step": 7750
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.493103448275862e-05,
+      "loss": 0.1018,
+      "step": 7775
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.48448275862069e-05,
+      "loss": 0.1017,
+      "step": 7800
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.4758620689655173e-05,
+      "loss": 0.1028,
+      "step": 7825
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.467241379310345e-05,
+      "loss": 0.0994,
+      "step": 7850
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.4586206896551725e-05,
+      "loss": 0.1049,
+      "step": 7875
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.45e-05,
+      "loss": 0.1005,
+      "step": 7900
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.4413793103448277e-05,
+      "loss": 0.1027,
+      "step": 7925
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.432758620689655e-05,
+      "loss": 0.1096,
+      "step": 7950
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 2.424137931034483e-05,
+      "loss": 0.0999,
+      "step": 7975
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.4155172413793103e-05,
+      "loss": 0.1021,
+      "step": 8000
+    },
+    {
+      "epoch": 2.96,
+      "eval_cer": 11.506672732787383,
+      "eval_loss": 0.2621135413646698,
+      "eval_runtime": 358.5537,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.901,
+      "step": 8000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.4068965517241378e-05,
+      "loss": 0.0984,
+      "step": 8025
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.398275862068966e-05,
+      "loss": 0.0976,
+      "step": 8050
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.3896551724137933e-05,
+      "loss": 0.1034,
+      "step": 8075
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.3810344827586208e-05,
+      "loss": 0.1011,
+      "step": 8100
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 2.3724137931034485e-05,
+      "loss": 0.0651,
+      "step": 8125
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 2.363793103448276e-05,
+      "loss": 0.0473,
+      "step": 8150
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 2.3551724137931037e-05,
+      "loss": 0.0448,
+      "step": 8175
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 2.3465517241379312e-05,
+      "loss": 0.0473,
+      "step": 8200
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 2.3379310344827586e-05,
+      "loss": 0.0457,
+      "step": 8225
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 2.3293103448275864e-05,
+      "loss": 0.0451,
+      "step": 8250
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 2.3206896551724138e-05,
+      "loss": 0.0453,
+      "step": 8275
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 2.3120689655172416e-05,
+      "loss": 0.0502,
+      "step": 8300
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 2.303448275862069e-05,
+      "loss": 0.0471,
+      "step": 8325
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 2.2948275862068965e-05,
+      "loss": 0.0476,
+      "step": 8350
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 2.2862068965517242e-05,
+      "loss": 0.0473,
+      "step": 8375
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 2.2775862068965517e-05,
+      "loss": 0.0476,
+      "step": 8400
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 2.2689655172413794e-05,
+      "loss": 0.0466,
+      "step": 8425
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 2.2603448275862072e-05,
+      "loss": 0.0478,
+      "step": 8450
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 2.2517241379310347e-05,
+      "loss": 0.0464,
+      "step": 8475
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 2.2431034482758624e-05,
+      "loss": 0.0468,
+      "step": 8500
+    },
+    {
+      "epoch": 3.15,
+      "eval_cer": 11.332271762208068,
+      "eval_loss": 0.2711898386478424,
+      "eval_runtime": 359.6452,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.898,
+      "step": 8500
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 2.23448275862069e-05,
+      "loss": 0.0468,
+      "step": 8525
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 2.2258620689655173e-05,
+      "loss": 0.0526,
+      "step": 8550
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.217241379310345e-05,
+      "loss": 0.0465,
+      "step": 8575
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 2.2086206896551725e-05,
+      "loss": 0.0499,
+      "step": 8600
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.0466,
+      "step": 8625
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 2.1913793103448277e-05,
+      "loss": 0.0451,
+      "step": 8650
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 2.182758620689655e-05,
+      "loss": 0.047,
+      "step": 8675
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 2.174137931034483e-05,
+      "loss": 0.0482,
+      "step": 8700
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 2.1655172413793104e-05,
+      "loss": 0.0513,
+      "step": 8725
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 2.1568965517241378e-05,
+      "loss": 0.0483,
+      "step": 8750
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.1482758620689656e-05,
+      "loss": 0.0491,
+      "step": 8775
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 2.139655172413793e-05,
+      "loss": 0.0483,
+      "step": 8800
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 2.1310344827586208e-05,
+      "loss": 0.0504,
+      "step": 8825
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 2.1224137931034486e-05,
+      "loss": 0.0514,
+      "step": 8850
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 2.113793103448276e-05,
+      "loss": 0.0484,
+      "step": 8875
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 2.1051724137931038e-05,
+      "loss": 0.0474,
+      "step": 8900
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 2.0965517241379312e-05,
+      "loss": 0.0462,
+      "step": 8925
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 2.0879310344827586e-05,
+      "loss": 0.0501,
+      "step": 8950
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 2.0793103448275864e-05,
+      "loss": 0.0487,
+      "step": 8975
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 2.070689655172414e-05,
+      "loss": 0.0499,
+      "step": 9000
+    },
+    {
+      "epoch": 3.33,
+      "eval_cer": 11.555959963603275,
+      "eval_loss": 0.28167569637298584,
+      "eval_runtime": 359.0627,
+      "eval_samples_per_second": 7.188,
+      "eval_steps_per_second": 0.9,
+      "step": 9000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 2.0620689655172416e-05,
+      "loss": 0.0496,
+      "step": 9025
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 2.053448275862069e-05,
+      "loss": 0.0471,
+      "step": 9050
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 2.0448275862068965e-05,
+      "loss": 0.0469,
+      "step": 9075
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 2.0362068965517243e-05,
+      "loss": 0.0511,
+      "step": 9100
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 2.0275862068965517e-05,
+      "loss": 0.0476,
+      "step": 9125
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 2.0189655172413795e-05,
+      "loss": 0.0483,
+      "step": 9150
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.010344827586207e-05,
+      "loss": 0.0484,
+      "step": 9175
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.0017241379310343e-05,
+      "loss": 0.0524,
+      "step": 9200
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.993103448275862e-05,
+      "loss": 0.0469,
+      "step": 9225
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.98448275862069e-05,
+      "loss": 0.0454,
+      "step": 9250
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.9758620689655173e-05,
+      "loss": 0.0489,
+      "step": 9275
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 1.967241379310345e-05,
+      "loss": 0.0482,
+      "step": 9300
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.9586206896551725e-05,
+      "loss": 0.0487,
+      "step": 9325
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.048,
+      "step": 9350
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 1.9413793103448277e-05,
+      "loss": 0.0477,
+      "step": 9375
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.9327586206896552e-05,
+      "loss": 0.0511,
+      "step": 9400
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.924137931034483e-05,
+      "loss": 0.0468,
+      "step": 9425
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.9155172413793104e-05,
+      "loss": 0.0502,
+      "step": 9450
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.906896551724138e-05,
+      "loss": 0.0476,
+      "step": 9475
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.8982758620689656e-05,
+      "loss": 0.0489,
+      "step": 9500
+    },
+    {
+      "epoch": 3.52,
+      "eval_cer": 11.548377312708523,
+      "eval_loss": 0.28109079599380493,
+      "eval_runtime": 359.545,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.898,
+      "step": 9500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.889655172413793e-05,
+      "loss": 0.0463,
+      "step": 9525
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.8810344827586208e-05,
+      "loss": 0.0457,
+      "step": 9550
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 1.8724137931034482e-05,
+      "loss": 0.0463,
+      "step": 9575
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.863793103448276e-05,
+      "loss": 0.0526,
+      "step": 9600
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.8551724137931034e-05,
+      "loss": 0.0499,
+      "step": 9625
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 1.8465517241379312e-05,
+      "loss": 0.0488,
+      "step": 9650
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.837931034482759e-05,
+      "loss": 0.0491,
+      "step": 9675
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 1.8293103448275864e-05,
+      "loss": 0.046,
+      "step": 9700
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.820689655172414e-05,
+      "loss": 0.0475,
+      "step": 9725
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.8120689655172416e-05,
+      "loss": 0.0512,
+      "step": 9750
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.803448275862069e-05,
+      "loss": 0.0478,
+      "step": 9775
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.7948275862068965e-05,
+      "loss": 0.0602,
+      "step": 9800
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.7862068965517243e-05,
+      "loss": 0.0482,
+      "step": 9825
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7775862068965517e-05,
+      "loss": 0.0463,
+      "step": 9850
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7689655172413795e-05,
+      "loss": 0.0513,
+      "step": 9875
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.760344827586207e-05,
+      "loss": 0.0495,
+      "step": 9900
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.7517241379310344e-05,
+      "loss": 0.0547,
+      "step": 9925
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.743103448275862e-05,
+      "loss": 0.0485,
+      "step": 9950
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.7344827586206896e-05,
+      "loss": 0.0498,
+      "step": 9975
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.7258620689655173e-05,
+      "loss": 0.0479,
+      "step": 10000
+    },
+    {
+      "epoch": 3.7,
+      "eval_cer": 10.695329087048833,
+      "eval_loss": 0.27692216634750366,
+      "eval_runtime": 359.4994,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.898,
+      "step": 10000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.7172413793103448e-05,
+      "loss": 0.0456,
+      "step": 10025
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.7086206896551722e-05,
+      "loss": 0.0512,
+      "step": 10050
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.0487,
+      "step": 10075
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.6913793103448278e-05,
+      "loss": 0.0463,
+      "step": 10100
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.6827586206896552e-05,
+      "loss": 0.0625,
+      "step": 10125
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 1.674137931034483e-05,
+      "loss": 0.0474,
+      "step": 10150
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.6655172413793104e-05,
+      "loss": 0.0476,
+      "step": 10175
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.6568965517241382e-05,
+      "loss": 0.0502,
+      "step": 10200
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.6482758620689656e-05,
+      "loss": 0.0522,
+      "step": 10225
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.639655172413793e-05,
+      "loss": 0.0458,
+      "step": 10250
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.6310344827586208e-05,
+      "loss": 0.0482,
+      "step": 10275
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.6224137931034483e-05,
+      "loss": 0.0466,
+      "step": 10300
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 1.613793103448276e-05,
+      "loss": 0.0466,
+      "step": 10325
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.6051724137931035e-05,
+      "loss": 0.0451,
+      "step": 10350
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.596551724137931e-05,
+      "loss": 0.0492,
+      "step": 10375
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.5879310344827587e-05,
+      "loss": 0.045,
+      "step": 10400
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.579310344827586e-05,
+      "loss": 0.0457,
+      "step": 10425
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.570689655172414e-05,
+      "loss": 0.0471,
+      "step": 10450
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.5620689655172417e-05,
+      "loss": 0.0473,
+      "step": 10475
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.553448275862069e-05,
+      "loss": 0.049,
+      "step": 10500
+    },
+    {
+      "epoch": 3.89,
+      "eval_cer": 11.51046405823476,
+      "eval_loss": 0.28438711166381836,
+      "eval_runtime": 359.2212,
+      "eval_samples_per_second": 7.185,
+      "eval_steps_per_second": 0.899,
+      "step": 10500
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.544827586206897e-05,
+      "loss": 0.0458,
+      "step": 10525
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.5362068965517243e-05,
+      "loss": 0.0456,
+      "step": 10550
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.5275862068965517e-05,
+      "loss": 0.0474,
+      "step": 10575
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.5189655172413793e-05,
+      "loss": 0.0447,
+      "step": 10600
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 1.510344827586207e-05,
+      "loss": 0.046,
+      "step": 10625
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.5017241379310346e-05,
+      "loss": 0.0442,
+      "step": 10650
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 1.4931034482758622e-05,
+      "loss": 0.0457,
+      "step": 10675
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 1.4844827586206898e-05,
+      "loss": 0.0482,
+      "step": 10700
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.4758620689655172e-05,
+      "loss": 0.0476,
+      "step": 10725
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.4672413793103448e-05,
+      "loss": 0.0449,
+      "step": 10750
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.4586206896551724e-05,
+      "loss": 0.0478,
+      "step": 10775
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.45e-05,
+      "loss": 0.0517,
+      "step": 10800
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 1.4413793103448276e-05,
+      "loss": 0.0285,
+      "step": 10825
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 1.432758620689655e-05,
+      "loss": 0.0197,
+      "step": 10850
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 1.424137931034483e-05,
+      "loss": 0.0183,
+      "step": 10875
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.4155172413793106e-05,
+      "loss": 0.0186,
+      "step": 10900
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 1.406896551724138e-05,
+      "loss": 0.0203,
+      "step": 10925
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 1.3982758620689656e-05,
+      "loss": 0.0185,
+      "step": 10950
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 1.3896551724137932e-05,
+      "loss": 0.0173,
+      "step": 10975
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 1.3810344827586208e-05,
+      "loss": 0.0193,
+      "step": 11000
+    },
+    {
+      "epoch": 4.07,
+      "eval_cer": 11.116166211707613,
+      "eval_loss": 0.29933854937553406,
+      "eval_runtime": 359.5628,
+      "eval_samples_per_second": 7.178,
+      "eval_steps_per_second": 0.898,
+      "step": 11000
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 1.3724137931034484e-05,
+      "loss": 0.0176,
+      "step": 11025
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.3637931034482759e-05,
+      "loss": 0.0171,
+      "step": 11050
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 1.3551724137931035e-05,
+      "loss": 0.0173,
+      "step": 11075
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 1.3465517241379311e-05,
+      "loss": 0.0185,
+      "step": 11100
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.3379310344827587e-05,
+      "loss": 0.0161,
+      "step": 11125
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 1.3293103448275861e-05,
+      "loss": 0.0186,
+      "step": 11150
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 1.3206896551724137e-05,
+      "loss": 0.0191,
+      "step": 11175
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.3120689655172413e-05,
+      "loss": 0.0177,
+      "step": 11200
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.303448275862069e-05,
+      "loss": 0.0184,
+      "step": 11225
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.2948275862068966e-05,
+      "loss": 0.0195,
+      "step": 11250
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 1.2862068965517243e-05,
+      "loss": 0.019,
+      "step": 11275
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 1.277586206896552e-05,
+      "loss": 0.0183,
+      "step": 11300
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.2689655172413795e-05,
+      "loss": 0.0188,
+      "step": 11325
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 1.260344827586207e-05,
+      "loss": 0.0209,
+      "step": 11350
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 1.2517241379310346e-05,
+      "loss": 0.0171,
+      "step": 11375
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.2431034482758622e-05,
+      "loss": 0.0163,
+      "step": 11400
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 1.2344827586206898e-05,
+      "loss": 0.0181,
+      "step": 11425
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 1.2258620689655174e-05,
+      "loss": 0.0169,
+      "step": 11450
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 1.2172413793103448e-05,
+      "loss": 0.0197,
+      "step": 11475
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 1.2086206896551724e-05,
+      "loss": 0.0163,
+      "step": 11500
+    },
+    {
+      "epoch": 4.26,
+      "eval_cer": 11.010009099181074,
+      "eval_loss": 0.3046729266643524,
+      "eval_runtime": 358.1502,
+      "eval_samples_per_second": 7.206,
+      "eval_steps_per_second": 0.902,
+      "step": 11500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 1.2e-05,
+      "loss": 0.0174,
+      "step": 11525
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 1.1913793103448276e-05,
+      "loss": 0.0179,
+      "step": 11550
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 1.1827586206896552e-05,
+      "loss": 0.0189,
+      "step": 11575
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 1.1741379310344828e-05,
+      "loss": 0.0202,
+      "step": 11600
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 1.1655172413793104e-05,
+      "loss": 0.017,
+      "step": 11625
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 1.156896551724138e-05,
+      "loss": 0.0186,
+      "step": 11650
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 1.1482758620689655e-05,
+      "loss": 0.0193,
+      "step": 11675
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 1.1396551724137931e-05,
+      "loss": 0.0173,
+      "step": 11700
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 1.1310344827586207e-05,
+      "loss": 0.018,
+      "step": 11725
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 1.1224137931034483e-05,
+      "loss": 0.0166,
+      "step": 11750
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 1.1137931034482759e-05,
+      "loss": 0.0176,
+      "step": 11775
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 1.1051724137931035e-05,
+      "loss": 0.0195,
+      "step": 11800
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 1.0965517241379311e-05,
+      "loss": 0.0179,
+      "step": 11825
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 1.0879310344827587e-05,
+      "loss": 0.0174,
+      "step": 11850
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 1.0793103448275863e-05,
+      "loss": 0.0183,
+      "step": 11875
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.0706896551724138e-05,
+      "loss": 0.0178,
+      "step": 11900
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 1.0620689655172414e-05,
+      "loss": 0.0177,
+      "step": 11925
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 1.053448275862069e-05,
+      "loss": 0.0186,
+      "step": 11950
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 1.0448275862068967e-05,
+      "loss": 0.0174,
+      "step": 11975
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.0362068965517242e-05,
+      "loss": 0.0175,
+      "step": 12000
+    },
+    {
+      "epoch": 4.44,
+      "eval_cer": 10.911434637549288,
+      "eval_loss": 0.30570268630981445,
+      "eval_runtime": 358.4295,
+      "eval_samples_per_second": 7.201,
+      "eval_steps_per_second": 0.901,
+      "step": 12000
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 1.0275862068965518e-05,
+      "loss": 0.019,
+      "step": 12025
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 1.0189655172413794e-05,
+      "loss": 0.0179,
+      "step": 12050
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 1.010344827586207e-05,
+      "loss": 0.0192,
+      "step": 12075
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 1.0017241379310344e-05,
+      "loss": 0.0167,
+      "step": 12100
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 9.93103448275862e-06,
+      "loss": 0.0178,
+      "step": 12125
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 9.844827586206896e-06,
+      "loss": 0.0209,
+      "step": 12150
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 9.758620689655174e-06,
+      "loss": 0.019,
+      "step": 12175
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 9.672413793103448e-06,
+      "loss": 0.0169,
+      "step": 12200
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 9.586206896551724e-06,
+      "loss": 0.0175,
+      "step": 12225
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 9.5e-06,
+      "loss": 0.0166,
+      "step": 12250
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 9.413793103448277e-06,
+      "loss": 0.0184,
+      "step": 12275
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 9.327586206896553e-06,
+      "loss": 0.0256,
+      "step": 12300
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 9.241379310344827e-06,
+      "loss": 0.0177,
+      "step": 12325
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 9.155172413793103e-06,
+      "loss": 0.018,
+      "step": 12350
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 9.06896551724138e-06,
+      "loss": 0.0187,
+      "step": 12375
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 8.982758620689657e-06,
+      "loss": 0.0175,
+      "step": 12400
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 8.896551724137931e-06,
+      "loss": 0.0204,
+      "step": 12425
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 8.810344827586207e-06,
+      "loss": 0.0177,
+      "step": 12450
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 8.724137931034483e-06,
+      "loss": 0.0174,
+      "step": 12475
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 8.63793103448276e-06,
+      "loss": 0.0186,
+      "step": 12500
+    },
+    {
+      "epoch": 4.63,
+      "eval_cer": 11.127540188049743,
+      "eval_loss": 0.30721473693847656,
+      "eval_runtime": 359.2661,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 0.899,
+      "step": 12500
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 8.555172413793104e-06,
+      "loss": 0.0166,
+      "step": 12525
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 8.46896551724138e-06,
+      "loss": 0.0196,
+      "step": 12550
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 8.382758620689656e-06,
+      "loss": 0.0187,
+      "step": 12575
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 8.296551724137932e-06,
+      "loss": 0.0179,
+      "step": 12600
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 8.210344827586206e-06,
+      "loss": 0.016,
+      "step": 12625
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 8.124137931034482e-06,
+      "loss": 0.022,
+      "step": 12650
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 8.03793103448276e-06,
+      "loss": 0.0156,
+      "step": 12675
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 7.951724137931036e-06,
+      "loss": 0.0172,
+      "step": 12700
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 7.86551724137931e-06,
+      "loss": 0.0188,
+      "step": 12725
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 7.779310344827586e-06,
+      "loss": 0.0208,
+      "step": 12750
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 7.693103448275862e-06,
+      "loss": 0.0176,
+      "step": 12775
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 7.6068965517241385e-06,
+      "loss": 0.018,
+      "step": 12800
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 7.520689655172414e-06,
+      "loss": 0.0168,
+      "step": 12825
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 7.43448275862069e-06,
+      "loss": 0.0159,
+      "step": 12850
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 7.348275862068967e-06,
+      "loss": 0.0166,
+      "step": 12875
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 7.262068965517242e-06,
+      "loss": 0.0182,
+      "step": 12900
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 7.175862068965518e-06,
+      "loss": 0.0166,
+      "step": 12925
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 7.089655172413794e-06,
+      "loss": 0.0168,
+      "step": 12950
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 7.003448275862069e-06,
+      "loss": 0.0174,
+      "step": 12975
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 6.917241379310345e-06,
+      "loss": 0.0176,
+      "step": 13000
+    },
+    {
+      "epoch": 4.81,
+      "eval_cer": 11.229905975128904,
+      "eval_loss": 0.30905863642692566,
+      "eval_runtime": 359.315,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.899,
+      "step": 13000
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 6.83103448275862e-06,
+      "loss": 0.0175,
+      "step": 13025
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 6.744827586206896e-06,
+      "loss": 0.017,
+      "step": 13050
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 6.658620689655173e-06,
+      "loss": 0.0158,
+      "step": 13075
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 6.572413793103449e-06,
+      "loss": 0.0182,
+      "step": 13100
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 6.4862068965517245e-06,
+      "loss": 0.0175,
+      "step": 13125
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.0191,
+      "step": 13150
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 6.313793103448276e-06,
+      "loss": 0.0153,
+      "step": 13175
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 6.227586206896552e-06,
+      "loss": 0.0197,
+      "step": 13200
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 6.141379310344828e-06,
+      "loss": 0.0165,
+      "step": 13225
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 6.055172413793104e-06,
+      "loss": 0.0157,
+      "step": 13250
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 5.96896551724138e-06,
+      "loss": 0.0156,
+      "step": 13275
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 5.882758620689655e-06,
+      "loss": 0.0175,
+      "step": 13300
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 5.796551724137932e-06,
+      "loss": 0.0166,
+      "step": 13325
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 5.710344827586207e-06,
+      "loss": 0.016,
+      "step": 13350
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 5.624137931034483e-06,
+      "loss": 0.0146,
+      "step": 13375
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 5.5379310344827585e-06,
+      "loss": 0.0181,
+      "step": 13400
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 5.451724137931035e-06,
+      "loss": 0.016,
+      "step": 13425
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 5.3655172413793106e-06,
+      "loss": 0.0186,
+      "step": 13450
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 5.279310344827587e-06,
+      "loss": 0.0157,
+      "step": 13475
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.193103448275862e-06,
+      "loss": 0.0173,
+      "step": 13500
+    },
+    {
+      "epoch": 5.0,
+      "eval_cer": 11.082044282681224,
+      "eval_loss": 0.31240326166152954,
+      "eval_runtime": 358.0319,
+      "eval_samples_per_second": 7.209,
+      "eval_steps_per_second": 0.902,
+      "step": 13500
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 5.106896551724139e-06,
+      "loss": 0.0115,
+      "step": 13525
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 5.020689655172414e-06,
+      "loss": 0.0083,
+      "step": 13550
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 4.93448275862069e-06,
+      "loss": 0.0078,
+      "step": 13575
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 4.848275862068966e-06,
+      "loss": 0.0081,
+      "step": 13600
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 4.762068965517242e-06,
+      "loss": 0.007,
+      "step": 13625
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 4.675862068965517e-06,
+      "loss": 0.008,
+      "step": 13650
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.589655172413793e-06,
+      "loss": 0.0076,
+      "step": 13675
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 4.503448275862069e-06,
+      "loss": 0.0093,
+      "step": 13700
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 4.417241379310345e-06,
+      "loss": 0.0073,
+      "step": 13725
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 4.331034482758621e-06,
+      "loss": 0.0072,
+      "step": 13750
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 4.244827586206897e-06,
+      "loss": 0.0079,
+      "step": 13775
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 4.158620689655173e-06,
+      "loss": 0.0076,
+      "step": 13800
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 4.072413793103449e-06,
+      "loss": 0.0071,
+      "step": 13825
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 3.986206896551725e-06,
+      "loss": 0.0071,
+      "step": 13850
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 3.9e-06,
+      "loss": 0.0067,
+      "step": 13875
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 3.813793103448276e-06,
+      "loss": 0.0077,
+      "step": 13900
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 3.7275862068965524e-06,
+      "loss": 0.0089,
+      "step": 13925
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 3.641379310344828e-06,
+      "loss": 0.0077,
+      "step": 13950
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 3.5551724137931037e-06,
+      "loss": 0.008,
+      "step": 13975
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 3.4689655172413793e-06,
+      "loss": 0.007,
+      "step": 14000
+    },
+    {
+      "epoch": 5.18,
+      "eval_cer": 10.862147406733394,
+      "eval_loss": 0.3205486238002777,
+      "eval_runtime": 361.4728,
+      "eval_samples_per_second": 7.14,
+      "eval_steps_per_second": 0.894,
+      "step": 14000
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 3.382758620689655e-06,
+      "loss": 0.0088,
+      "step": 14025
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 3.2965517241379314e-06,
+      "loss": 0.0072,
+      "step": 14050
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 3.210344827586207e-06,
+      "loss": 0.0085,
+      "step": 14075
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 3.1241379310344826e-06,
+      "loss": 0.0068,
+      "step": 14100
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 3.0379310344827587e-06,
+      "loss": 0.0081,
+      "step": 14125
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 2.9517241379310343e-06,
+      "loss": 0.0074,
+      "step": 14150
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 2.8655172413793104e-06,
+      "loss": 0.0077,
+      "step": 14175
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.779310344827586e-06,
+      "loss": 0.0083,
+      "step": 14200
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.693103448275862e-06,
+      "loss": 0.008,
+      "step": 14225
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 2.606896551724138e-06,
+      "loss": 0.0064,
+      "step": 14250
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 2.520689655172414e-06,
+      "loss": 0.0076,
+      "step": 14275
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 2.4344827586206897e-06,
+      "loss": 0.0066,
+      "step": 14300
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 2.3482758620689658e-06,
+      "loss": 0.008,
+      "step": 14325
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 2.2620689655172414e-06,
+      "loss": 0.0072,
+      "step": 14350
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 2.1758620689655174e-06,
+      "loss": 0.0078,
+      "step": 14375
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 2.089655172413793e-06,
+      "loss": 0.0091,
+      "step": 14400
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 2.003448275862069e-06,
+      "loss": 0.007,
+      "step": 14425
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 1.9172413793103447e-06,
+      "loss": 0.0078,
+      "step": 14450
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 1.8310344827586208e-06,
+      "loss": 0.0074,
+      "step": 14475
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 1.7448275862068964e-06,
+      "loss": 0.0073,
+      "step": 14500
+    },
+    {
+      "epoch": 5.37,
+      "eval_cer": 10.790112223233242,
+      "eval_loss": 0.320094496011734,
+      "eval_runtime": 359.2372,
+      "eval_samples_per_second": 7.185,
+      "eval_steps_per_second": 0.899,
+      "step": 14500
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 1.6586206896551724e-06,
+      "loss": 0.0094,
+      "step": 14525
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 1.5724137931034483e-06,
+      "loss": 0.0142,
+      "step": 14550
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 1.4862068965517243e-06,
+      "loss": 0.0085,
+      "step": 14575
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 1.4034482758620691e-06,
+      "loss": 0.0113,
+      "step": 14600
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 1.317241379310345e-06,
+      "loss": 0.0085,
+      "step": 14625
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 1.2310344827586208e-06,
+      "loss": 0.0076,
+      "step": 14650
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 1.1448275862068966e-06,
+      "loss": 0.0074,
+      "step": 14675
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 1.0586206896551725e-06,
+      "loss": 0.0079,
+      "step": 14700
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 9.724137931034483e-07,
+      "loss": 0.0067,
+      "step": 14725
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 8.862068965517242e-07,
+      "loss": 0.0075,
+      "step": 14750
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.0082,
+      "step": 14775
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 7.137931034482759e-07,
+      "loss": 0.008,
+      "step": 14800
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 6.275862068965517e-07,
+      "loss": 0.0066,
+      "step": 14825
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 5.413793103448277e-07,
+      "loss": 0.0077,
+      "step": 14850
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 4.551724137931035e-07,
+      "loss": 0.0075,
+      "step": 14875
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 3.689655172413793e-07,
+      "loss": 0.0086,
+      "step": 14900
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 2.827586206896552e-07,
+      "loss": 0.0067,
+      "step": 14925
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 1.9655172413793103e-07,
+      "loss": 0.0075,
+      "step": 14950
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 1.1034482758620691e-07,
+      "loss": 0.0067,
+      "step": 14975
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 2.413793103448276e-08,
+      "loss": 0.0072,
+      "step": 15000
+    },
+    {
+      "epoch": 5.55,
+      "eval_cer": 10.763572945101608,
+      "eval_loss": 0.3218766450881958,
+      "eval_runtime": 359.0558,
+      "eval_samples_per_second": 7.188,
+      "eval_steps_per_second": 0.9,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 4.328506848669696e+20,
+  "train_batch_size": 25,
+  "trial_name": null,
+  "trial_params": null
+}

audio_model_states/whisper-small-cantonese/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b9840ed01e73c6d3c78f79f6c07a4c43b0f2853aa99d1bb368c2d4b5439c8c
+size 5048

lfs.sh

@@ -0,0 +1,2 @@
+git lfs install
+huggingface-cli lfs-enable-largefiles .