Model save

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-base
+tags:
+- generated_from_trainer
+datasets:
+- generator
+metrics:
+- wer
+model-index:
+- name: whisper-base_ro-80mel
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: generator
+      type: generator
+      config: default
+      split: None
+      args: default
+    metrics:
+    - name: Wer
+      type: wer
+      value: 3.7315020227065117
+---
+
+<!-- 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-base_ro-80mel
+
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1412
+- Wer: 3.7315
+- Cer: 3.4131
+
+## 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: 2e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 96
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 1600
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 0.2048        | 1.0   | 2159  | 0.2050          | 3.8307 | 3.5327 |
+| 0.1214        | 2.0   | 4318  | 0.1410          | 3.7612 | 3.4390 |
+| 0.0764        | 3.0   | 6477  | 0.1242          | 4.2957 | 3.7273 |
+| 0.0486        | 4.0   | 8636  | 0.1212          | 4.3892 | 3.9276 |
+| 0.0329        | 5.0   | 10795 | 0.1218          | 4.4882 | 4.0181 |
+
+
+### Framework versions
+
+- Transformers 4.57.0
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 3.4130705016234986,
+    "eval_loss": 0.14117088913917542,
+    "eval_runtime": 1426.6353,
+    "eval_samples_per_second": 19.048,
+    "eval_steps_per_second": 0.794,
+    "eval_wer": 3.7315020227065117
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 3.4130705016234986,
+    "eval_loss": 0.14117088913917542,
+    "eval_runtime": 1426.6353,
+    "eval_samples_per_second": 19.048,
+    "eval_steps_per_second": 0.794,
+    "eval_wer": 3.7315020227065117
+}

final_best/config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50284
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

final_best/generation_config.json

@@ -0,0 +1,167 @@
+{
+  "alignment_heads": [
+    [
+      3,
+      1
+    ],
+    [
+      4,
+      2
+    ],
+    [
+      4,
+      3
+    ],
+    [
+      4,
+      7
+    ],
+    [
+      5,
+      1
+    ],
+    [
+      5,
+      2
+    ],
+    [
+      5,
+      4
+    ],
+    [
+      5,
+      6
+    ]
+  ],
+  "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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.0"
+}

final_best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f322db62b7f93d8c1575b22e5162ee15b30a3acb85f6cf40a1f1a039fa2869
+size 290403936

final_best/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
+}

final_best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23700856d88d253a23832bbde43219c30963594a3e78343d0ce8b1d2f10e957b
+size 6033

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6e7b163acfc155f430fde0b1cd7f4c8aa82b62cc3b337f7950c2e1a9de7901
+oid sha256:a8f322db62b7f93d8c1575b22e5162ee15b30a3acb85f6cf40a1f1a039fa2869
 size 290403936