Model save

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-hi2_test
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
+This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5291
 - Wer: 63.6040

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-tiny",
+  "_name_or_path": "./whisper-tiny-hi2_test/whisper-tiny-hi-checkpoint-1",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

runs/Jun20_07-41-26_bharatsahaiyak-test/events.out.tfevents.1718869287.bharatsahaiyak-test.505065.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2cf272083b8469c853e9a6c0a41ad5158ed6496bc17d433226be899ab555562
+size 6044

runs/Jun20_07-41-26_bharatsahaiyak-test/events.out.tfevents.1718869846.bharatsahaiyak-test.505065.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af5e74380fe61b2074b17ac1ccc46acd88711215ffa6bd282b205a25eafb11f
+size 406

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b00aa1f8925d482dd1ad48e165b81cd8051f3b752e0716117669ce7c5b2e10
+oid sha256:96ff286bdab46917ec7269a5c1949a3be1e038a7df16afe7f24c0e4862fa0eb7
 size 5240

whisper-tiny-hi-checkpoint-1/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 65.3061224489796,
+  "best_metric": 63.60403082394783,
   "best_model_checkpoint": "./whisper-tiny-hi2_test/checkpoint-200",
   "epoch": 6.25,
   "eval_steps": 40,
@@ -10,127 +10,127 @@
   "log_history": [
     {
       "epoch": 0.625,
-      "grad_norm": 10.625165939331055,
+      "grad_norm": 10.62358283996582,
       "learning_rate": 1e-05,
       "loss": 2.3669,
       "step": 20
     },
     {
       "epoch": 1.25,
-      "grad_norm": 7.56988525390625,
+      "grad_norm": 7.5668721199035645,
       "learning_rate": 1e-05,
-      "loss": 1.1886,
+      "loss": 1.1887,
       "step": 40
     },
     {
       "epoch": 1.25,
-      "eval_loss": 0.9953416585922241,
-      "eval_runtime": 569.1534,
-      "eval_samples_per_second": 1.757,
-      "eval_steps_per_second": 1.757,
-      "eval_wer": 87.39097298670505,
+      "eval_loss": 0.9953901171684265,
+      "eval_runtime": 571.1605,
+      "eval_samples_per_second": 1.751,
+      "eval_steps_per_second": 1.751,
+      "eval_wer": 87.29782369379288,
       "step": 40
     },
     {
       "epoch": 1.875,
-      "grad_norm": 6.930533409118652,
+      "grad_norm": 6.932765960693359,
       "learning_rate": 1e-05,
       "loss": 0.855,
       "step": 60
     },
     {
       "epoch": 2.5,
-      "grad_norm": 6.594748020172119,
+      "grad_norm": 6.589940547943115,
       "learning_rate": 1e-05,
       "loss": 0.6663,
       "step": 80
     },
     {
       "epoch": 2.5,
-      "eval_loss": 0.6780995726585388,
-      "eval_runtime": 553.0571,
-      "eval_samples_per_second": 1.808,
-      "eval_steps_per_second": 1.808,
-      "eval_wer": 73.2153442289779,
+      "eval_loss": 0.6780964136123657,
+      "eval_runtime": 554.1893,
+      "eval_samples_per_second": 1.804,
+      "eval_steps_per_second": 1.804,
+      "eval_wer": 73.29155728681515,
       "step": 80
     },
     {
       "epoch": 3.125,
-      "grad_norm": 6.1022748947143555,
+      "grad_norm": 6.102142810821533,
       "learning_rate": 1e-05,
       "loss": 0.5761,
       "step": 100
     },
     {
       "epoch": 3.75,
-      "grad_norm": 5.41855525970459,
+      "grad_norm": 5.4204583168029785,
       "learning_rate": 1e-05,
       "loss": 0.5053,
       "step": 120
     },
     {
       "epoch": 3.75,
-      "eval_loss": 0.5857406258583069,
-      "eval_runtime": 552.994,
-      "eval_samples_per_second": 1.808,
-      "eval_steps_per_second": 1.808,
-      "eval_wer": 66.17833855533914,
+      "eval_loss": 0.5857690572738647,
+      "eval_runtime": 567.8481,
+      "eval_samples_per_second": 1.761,
+      "eval_steps_per_second": 1.761,
+      "eval_wer": 66.22914726056398,
       "step": 120
     },
     {
       "epoch": 4.375,
-      "grad_norm": 4.851699352264404,
+      "grad_norm": 4.851945400238037,
       "learning_rate": 1e-05,
       "loss": 0.4369,
       "step": 140
     },
     {
       "epoch": 5.0,
-      "grad_norm": 9.787827491760254,
+      "grad_norm": 9.788898468017578,
       "learning_rate": 1e-05,
       "loss": 0.406,
       "step": 160
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.5440071225166321,
-      "eval_runtime": 541.8179,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 1.846,
-      "eval_wer": 66.11059361503938,
+      "eval_loss": 0.5440137982368469,
+      "eval_runtime": 560.2795,
+      "eval_samples_per_second": 1.785,
+      "eval_steps_per_second": 1.785,
+      "eval_wer": 66.13599796765179,
       "step": 160
     },
     {
       "epoch": 5.625,
-      "grad_norm": 4.657484531402588,
+      "grad_norm": 4.664266109466553,
       "learning_rate": 1e-05,
       "loss": 0.356,
       "step": 180
     },
     {
       "epoch": 6.25,
-      "grad_norm": 4.622303009033203,
+      "grad_norm": 4.6183037757873535,
       "learning_rate": 1e-05,
       "loss": 0.3236,
       "step": 200
     },
     {
       "epoch": 6.25,
-      "eval_loss": 0.5291295051574707,
-      "eval_runtime": 538.5029,
-      "eval_samples_per_second": 1.857,
-      "eval_steps_per_second": 1.857,
-      "eval_wer": 65.3061224489796,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 553.81,
+      "eval_samples_per_second": 1.806,
+      "eval_steps_per_second": 1.806,
+      "eval_wer": 63.60403082394783,
       "step": 200
     },
     {
       "epoch": 6.25,
       "step": 200,
       "total_flos": 1.5401574531072e+17,
-      "train_loss": 0.7680728721618653,
-      "train_runtime": 3566.0921,
-      "train_samples_per_second": 1.795,
-      "train_steps_per_second": 0.056
+      "train_loss": 0.7680861353874207,
+      "train_runtime": 3626.9505,
+      "train_samples_per_second": 1.765,
+      "train_steps_per_second": 0.055
     }
   ],
   "logging_steps": 20,

whisper-tiny-hi-checkpoint-2/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "./whisper-tiny-hi2_test/whisper-tiny-hi-checkpoint-1",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "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": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

whisper-tiny-hi-checkpoint-2/generation_config.json

@@ -0,0 +1,248 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|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,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|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,
+    "<|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,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "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
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.41.1"
+}

whisper-tiny-hi-checkpoint-2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65486a040e9edffe3575e458f27f57a36d8b2427a1a78dbd727b53bf7ff9bc9a
+size 151061672

whisper-tiny-hi-checkpoint-2/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
+}

whisper-tiny-hi-checkpoint-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ff286bdab46917ec7269a5c1949a3be1e038a7df16afe7f24c0e4862fa0eb7
+size 5240