End of training

README.md

@@ -0,0 +1,100 @@
+---
+library_name: transformers
+language:
+- ru
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- hf-asr-leaderboard
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_17_0
+metrics:
+- wer
+model-index:
+- name: Whisper Small ru - slowlydoor
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 17.0
+      type: mozilla-foundation/common_voice_17_0
+      config: ru
+      split: None
+      args: 'config: ru, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 16.040464106107944
+---
+
+<!-- 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 ru - slowlydoor
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2125
+- Wer: 16.0405
+- Cer: 4.2321
+- Ser: 57.5223
+
+## 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: 8
+- eval_batch_size: 4
+- seed: 42
+- 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
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Cer    | Validation Loss | Ser     | Wer     |
+|:-------------:|:------:|:----:|:------:|:---------------:|:-------:|:-------:|
+| 0.2206        | 0.1516 | 500  | 5.4963 | 0.2603          | 69.4306 | 21.2669 |
+| 0.22          | 0.3032 | 1000 | 5.3823 | 0.2467          | 67.3527 | 20.2971 |
+| 0.1901        | 0.4548 | 1500 | 5.1160 | 0.2377          | 66.1766 | 19.5642 |
+| 0.1969        | 0.6064 | 2000 | 5.0754 | 0.2273          | 64.3242 | 19.0509 |
+| 0.1743        | 0.7580 | 2500 | 4.8523 | 0.2188          | 63.1481 | 18.2286 |
+| 0.1747        | 0.9096 | 3000 | 4.8867 | 0.2167          | 62.4032 | 18.0985 |
+| 0.077         | 1.0612 | 3500 | 4.5272 | 0.2142          | 60.5998 | 17.2007 |
+| 0.0839        | 1.2129 | 4000 | 4.4628 | 0.2126          | 60.8743 | 17.1601 |
+| 0.0888        | 1.3645 | 4500 | 4.4864 | 0.2092          | 60.3940 | 17.3529 |
+| 0.069         | 1.5161 | 5000 | 4.4667 | 0.2118          | 60.1588 | 17.1578 |
+| 0.0609        | 1.6677 | 5500 | 4.4298 | 0.2077          | 59.3355 | 16.8546 |
+| 0.0721        | 1.8193 | 6000 | 4.3442 | 0.2060          | 58.6592 | 16.5527 |
+| 0.0681        | 1.9709 | 6500 | 4.3284 | 0.2038          | 58.1692 | 16.3575 |
+| 0.0322        | 2.1225 | 7000 | 0.2130 | 16.2809         | 4.2709  | 57.7771 |
+| 0.0277        | 2.2741 | 7500 | 0.2151 | 16.1067         | 4.2543  | 57.4733 |
+| 0.0249        | 2.4257 | 8000 | 0.2130 | 16.0741         | 4.2513  | 57.4635 |
+| 0.0234        | 2.5773 | 8500 | 0.2150 | 16.2600         | 4.2832  | 57.6693 |
+| 0.0264        | 2.7289 | 9000 | 0.2145 | 16.1160         | 4.2645  | 57.6301 |
+| 0.0268        | 2.8805 | 9500 | 0.2125 | 16.0405         | 4.2321  | 57.5223 |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

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": 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": [
+    [
+      1,
+      50263
+    ],
+    [
+      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": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

events.out.tfevents.1748552133.1be8c16b1302.2024.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161364d0939fac4fafe22dddabb25dee646c75e38437e8a8de5ff6511e148b45
+size 70234

events.out.tfevents.1748639559.edaa1010b6c7.1830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bae9371e36282a8e25fa1ddebee3f8f9dcefeffaa2d725895b37dead0508e2d
+size 9994

events.out.tfevents.1748646150.edaa1010b6c7.1830.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b075c8291d2b30be65c856469a17a68415ecb3ff0de4cb10fb376d638389d8c
+size 10019

events.out.tfevents.1748659635.426209ca1afa.3468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061fb26374505c8dfb964088630ce70eba1a55705a77b5c73028d5295d384cde
+size 37187

generation_config.json

@@ -0,0 +1,165 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "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": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ae75dd7f2f81f48a24b9b1c0b46ee1031313b9debc5ab97b8633b73afd9d83
+size 966995080

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b38eee52b411c89d8673d023f90e3f61f94622be847e6ed84d72c3f6eadeab7
+size 5432