初始化项目，由ModelHub XC社区提供模型

Model: octava/whisper-small-ablation-add-NLD-90 Source: Original Platform
2026-05-08 15:19:59 +08:00
commit 296a385b11
24 changed files with 117899 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
+*.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,81 @@
+---
+base_model: openai/whisper-small
+datasets:
+- fleurs
+library_name: transformers
+license: apache-2.0
+metrics:
+- wer
+tags:
+- generated_from_trainer
+model-index:
+- name: whisper-small-ablation-add-NLD-90
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: fleurs
+      type: fleurs
+      config: id_id
+      split: None
+      args: id_id
+    metrics:
+    - type: wer
+      value: 17.5811209439528
+      name: Wer
+---
+
+<!-- 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-ablation-add-NLD-90
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4254
+- Wer: 17.5811
+
+## 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: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.2897        | 0.5263 | 200  | 0.4269          | 18.6726 |
+| 0.177         | 1.0526 | 400  | 0.4194          | 18.0826 |
+| 0.1516        | 1.5789 | 600  | 0.4377          | 17.9720 |
+| 0.0713        | 2.1053 | 800  | 0.4025          | 17.8319 |
+| 0.074         | 2.6316 | 1000 | 0.4254          | 17.5811 |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.11.0+cu130
+- Datasets 3.0.1
+- Tokenizers 0.20.0
--- a/added_tokens.json
+++ b/added_tokens.json
--- a/config.json
+++ b/config.json
@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "./whisper-small-ablation-add-NLD-90",
+  "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,
+      50259
+    ],
+    [
+      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": "4.45.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,254 @@
+{
+  "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
+  },
+  "language": "indonesian",
+  "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,
+    50360,
+    50361,
+    50362
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.45.0"
+}
--- a/last-checkpoint/config.json
+++ b/last-checkpoint/config.json
@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "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,
+      50259
+    ],
+    [
+      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": "4.45.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
--- a/last-checkpoint/generation_config.json
+++ b/last-checkpoint/generation_config.json
@@ -0,0 +1,254 @@
+{
+  "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
+  },
+  "language": "indonesian",
+  "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,
+    50360,
+    50361,
+    50362
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.45.0"
+}
--- a/last-checkpoint/model.safetensors
+++ b/last-checkpoint/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcc1fead33a388281429d6004831d16730608f5436b52061b2105986a534266
+size 966995080
--- a/last-checkpoint/optimizer.pt
+++ b/last-checkpoint/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bac9a2fd93ec72b2b6fd65ffe53be791b43406c060164b46b77d4835c1dc42
+size 1925064509
--- a/last-checkpoint/preprocessor_config.json
+++ b/last-checkpoint/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
+}
--- a/last-checkpoint/rng_state.pth
+++ b/last-checkpoint/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824ec905a8cf4747a5cb5e3f23bd4ca6aa45be9a752cd12d183946dae871a3e0
+size 14645
--- a/last-checkpoint/scheduler.pt
+++ b/last-checkpoint/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9622aae11a03e028825c47221d7669598756a36f957434fcb782f37c242759a5
+size 1465
--- a/last-checkpoint/trainer_state.json
+++ b/last-checkpoint/trainer_state.json
@@ -0,0 +1,358 @@
+{
+  "best_metric": 17.5811209439528,
+  "best_model_checkpoint": "./whisper-small-ablation-add-NLD-90/checkpoint-1000",
+  "epoch": 2.6315789473684212,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 21.71042823791504,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.538,
+      "step": 25
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 17.377655029296875,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.2262,
+      "step": 50
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 7.760909080505371,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7052,
+      "step": 75
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 6.189646244049072,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.4282,
+      "step": 100
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 4.806670188903809,
+      "learning_rate": 2.5e-06,
+      "loss": 0.3623,
+      "step": 125
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 5.8449554443359375,
+      "learning_rate": 3e-06,
+      "loss": 0.349,
+      "step": 150
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 6.015202522277832,
+      "learning_rate": 3.5e-06,
+      "loss": 0.3177,
+      "step": 175
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 5.104579925537109,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.2897,
+      "step": 200
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 0.42691341042518616,
+      "eval_runtime": 104.1539,
+      "eval_samples_per_second": 6.596,
+      "eval_steps_per_second": 0.413,
+      "eval_wer": 18.672566371681416,
+      "step": 200
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 4.69817590713501,
+      "learning_rate": 4.5e-06,
+      "loss": 0.3183,
+      "step": 225
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 6.035786151885986,
+      "learning_rate": 5e-06,
+      "loss": 0.2797,
+      "step": 250
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 5.456104755401611,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.2788,
+      "step": 275
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 6.070672988891602,
+      "learning_rate": 6e-06,
+      "loss": 0.2551,
+      "step": 300
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 5.564907073974609,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.2558,
+      "step": 325
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 5.393413066864014,
+      "learning_rate": 7e-06,
+      "loss": 0.2507,
+      "step": 350
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 4.764667987823486,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2429,
+      "step": 375
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 4.35653018951416,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.177,
+      "step": 400
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "eval_loss": 0.41943758726119995,
+      "eval_runtime": 105.1972,
+      "eval_samples_per_second": 6.531,
+      "eval_steps_per_second": 0.409,
+      "eval_wer": 18.08259587020649,
+      "step": 400
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 4.236116409301758,
+      "learning_rate": 8.5e-06,
+      "loss": 0.1628,
+      "step": 425
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 4.181164264678955,
+      "learning_rate": 9e-06,
+      "loss": 0.1728,
+      "step": 450
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.1720452308654785,
+      "learning_rate": 9.5e-06,
+      "loss": 0.1684,
+      "step": 475
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 4.402536392211914,
+      "learning_rate": 1e-05,
+      "loss": 0.1662,
+      "step": 500
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 4.496105194091797,
+      "learning_rate": 9.5e-06,
+      "loss": 0.1589,
+      "step": 525
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 5.0732598304748535,
+      "learning_rate": 9e-06,
+      "loss": 0.1757,
+      "step": 550
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 4.759901523590088,
+      "learning_rate": 8.5e-06,
+      "loss": 0.16,
+      "step": 575
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 4.546085357666016,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1516,
+      "step": 600
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.4376579523086548,
+      "eval_runtime": 104.9438,
+      "eval_samples_per_second": 6.546,
+      "eval_steps_per_second": 0.41,
+      "eval_wer": 17.97197640117994,
+      "step": 600
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 4.176891326904297,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.1631,
+      "step": 625
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 4.341442584991455,
+      "learning_rate": 7e-06,
+      "loss": 0.1645,
+      "step": 650
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 3.9501426219940186,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.155,
+      "step": 675
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 3.759936809539795,
+      "learning_rate": 6e-06,
+      "loss": 0.156,
+      "step": 700
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 3.296854257583618,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.1545,
+      "step": 725
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 4.553784370422363,
+      "learning_rate": 5e-06,
+      "loss": 0.1481,
+      "step": 750
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 1.8281787633895874,
+      "learning_rate": 4.5e-06,
+      "loss": 0.1124,
+      "step": 775
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.578198194503784,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0713,
+      "step": 800
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "eval_loss": 0.4024522602558136,
+      "eval_runtime": 104.903,
+      "eval_samples_per_second": 6.549,
+      "eval_steps_per_second": 0.41,
+      "eval_wer": 17.831858407079647,
+      "step": 800
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 2.781614065170288,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0723,
+      "step": 825
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 3.354801654815674,
+      "learning_rate": 3e-06,
+      "loss": 0.0653,
+      "step": 850
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 2.1840062141418457,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0729,
+      "step": 875
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 1.947718858718872,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0752,
+      "step": 900
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 1.8653781414031982,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0831,
+      "step": 925
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.6506271362304688,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.0695,
+      "step": 950
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 2.864332437515259,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.0686,
+      "step": 975
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 2.2327263355255127,
+      "learning_rate": 0.0,
+      "loss": 0.074,
+      "step": 1000
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "eval_loss": 0.425365149974823,
+      "eval_runtime": 104.7256,
+      "eval_samples_per_second": 6.56,
+      "eval_steps_per_second": 0.411,
+      "eval_wer": 17.5811209439528,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.220303540224e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/last-checkpoint/training_args.bin
+++ b/last-checkpoint/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d4fda8a52a2821362e63090c88c213d3454931555deb52040af3c3ed40000c
+size 5777
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9036f27f4e9afb4de69dc467dd13bbb1b35df130c8d865ed8c2baae08d54ef48
+size 966995080
--- a/normalizer.json
+++ b/normalizer.json
--- a/preprocessor_config.json
+++ b/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
+}
--- a/runs/May04_05-03-49_47e8a6f921db/events.out.tfevents.1777871030.47e8a6f921db.2362.3
+++ b/runs/May04_05-03-49_47e8a6f921db/events.out.tfevents.1777871030.47e8a6f921db.2362.3
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f4e6a507c358fb0ebec5aa88836467a2c3b1f6c5e71425c5fc4d95353bcd1b
+size 16166
--- a/runs/May06_13-22-03_a74e516a41c0/events.out.tfevents.1778073725.a74e516a41c0.2184.0
+++ b/runs/May06_13-22-03_a74e516a41c0/events.out.tfevents.1778073725.a74e516a41c0.2184.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a802c9a963da1248d955f97e1147fc18858d7dcde6c540ccb591f11439e3359d
+size 17120
--- a/special_tokens_map.json
+++ b/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|>",
+    "<|he|>",
+    "<|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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d4fda8a52a2821362e63090c88c213d3454931555deb52040af3c3ed40000c
+size 5777
--- a/vocab.json
+++ b/vocab.json