End of training

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+language:
+- en
+license: apache-2.0
+base_model: openai/whisper-tiny.en
+tags:
+- generated_from_trainer
+datasets:
+- maliced/l2-arctic
+model-index:
+- name: Whisper Tiny Phonemes
+  results: []
+---
+
+<!-- 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 Tiny Phonemes
+
+This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the L2 Arctic dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.52.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</S>": 41,
+  "<S>": 40,
+  "SIL": 42
+}

config.json

@@ -0,0 +1,101 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperCTCforTransformers"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "blank_token_id": 42,
+  "bos_token_id": 50256,
+  "classifier_proj_size": 256,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_end_token_id": 41,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 1,
+  "decoder_size": 43,
+  "decoder_start_token_id": 40,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50256,
+  "feature_size": 80,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "lexicon_path": "./lexicon.txt",
+  "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_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": 42,
+  "scale_embedding": false,
+  "size": "tiny",
+  "tokens": [
+    "SIL",
+    "AA",
+    "AE",
+    "AH",
+    "AO",
+    "AW",
+    "AX",
+    "AY",
+    "B",
+    "CH",
+    "D",
+    "DH",
+    "EH",
+    "ER",
+    "EY",
+    "F",
+    "G",
+    "HH",
+    "IH",
+    "IY",
+    "JH",
+    "K",
+    "L",
+    "M",
+    "N",
+    "NG",
+    "OW",
+    "OY",
+    "P",
+    "R",
+    "S",
+    "SH",
+    "T",
+    "TH",
+    "UH",
+    "UW",
+    "V",
+    "W",
+    "Y",
+    "Z",
+    "ZH",
+    "<S>",
+    "</S>"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51864
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c399f1f0460a66515c46905eb3b589ce0ff7ed453be7f7f3806b794699e787
+size 112711280

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "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
+}

runs/May28_08-36-44_876721f732e8/events.out.tfevents.1748421422.876721f732e8.475.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc99e72823917aaac226b51546e9f901cabadfb4cdfe66576f748e741c85d1a
+size 8491

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<S>",
+  "eos_token": "</S>",
+  "pad_token": "SIL",
+  "unk_token": "SIL"
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "added_tokens_decoder": {
+    "40": {
+      "content": "<S>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "</S>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "SIL",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<S>",
+  "clean_up_tokenization_spaces": false,
+  "do_phonemize": true,
+  "eos_token": "</S>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "SIL",
+  "phone_delimiter_token": " ",
+  "phonemizer_backend": "espeak",
+  "phonemizer_lang": "en-us",
+  "target_lang": "en-US",
+  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
+  "unk_token": "SIL",
+  "word_delimiter_token": "SIL"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ab79c67304baed5023e60914c7c6cb1a2bd8eda5b26fa20bec3dcb89fcf347
+size 5432

vocab.json

@@ -0,0 +1,42 @@
+{
+  "AA": 1,
+  "AE": 2,
+  "AH": 3,
+  "AO": 4,
+  "AW": 5,
+  "AX": 6,
+  "AY": 7,
+  "B": 8,
+  "CH": 9,
+  "D": 10,
+  "DH": 11,
+  "EH": 12,
+  "ER": 13,
+  "EY": 14,
+  "F": 15,
+  "G": 16,
+  "HH": 17,
+  "IH": 18,
+  "IY": 19,
+  "JH": 20,
+  "K": 21,
+  "L": 22,
+  "M": 23,
+  "N": 24,
+  "NG": 25,
+  "OW": 26,
+  "OY": 27,
+  "P": 28,
+  "R": 29,
+  "S": 30,
+  "SH": 31,
+  "T": 32,
+  "TH": 33,
+  "UH": 34,
+  "UW": 35,
+  "V": 36,
+  "W": 37,
+  "Y": 38,
+  "Z": 39,
+  "ZH": 40
+}