FunPang/whisper_base_atco2

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: model_whisper_base_atco2
+  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. -->
+
+# model_whisper_base_atco2
+
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1030
+- Wer: 7.3561
+
+## 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: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.2209        | 1.0   | 1012 | 0.1030          | 7.3561 |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu118
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "openai/whisper-base",
+  "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,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,247 @@
+{
+  "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,
+  "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": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84b8d7dbadab4f999cced03f250742d1759d5b75c6ac52218dea2768dcd848d
+size 290403936

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a02949c4aaaf824e45674b4cb9a687c008744296508b1efe9a133ca636bd3d
+size 574811514

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
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb743db0916254801973d53d82c55204e8a086c4546bb0080a1ef9be2e3d50f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191d9bf9658be16fd2b3b5cc60b13a11e875f234fb7d688dfb547d4a067434a8
+size 1064

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 4.021976178493541,
+  "best_model_checkpoint": "model_whisper_base_atco2\\checkpoint-9108",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 10120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.400457382202148,
+      "learning_rate": 1e-05,
+      "loss": 0.2212,
+      "step": 1012
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.10344767570495605,
+      "eval_runtime": 291.7326,
+      "eval_samples_per_second": 6.945,
+      "eval_steps_per_second": 0.871,
+      "eval_wer": 5.93440697869485,
+      "step": 1012
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.802471160888672,
+      "learning_rate": 1e-05,
+      "loss": 0.0619,
+      "step": 2024
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.09189248830080032,
+      "eval_runtime": 297.8017,
+      "eval_samples_per_second": 6.803,
+      "eval_steps_per_second": 0.853,
+      "eval_wer": 5.183694011071967,
+      "step": 2024
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.2378997802734375,
+      "learning_rate": 1e-05,
+      "loss": 0.0273,
+      "step": 3036
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.08819250017404556,
+      "eval_runtime": 287.7608,
+      "eval_samples_per_second": 7.041,
+      "eval_steps_per_second": 0.883,
+      "eval_wer": 4.495889951350445,
+      "step": 3036
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.339867353439331,
+      "learning_rate": 1e-05,
+      "loss": 0.0146,
+      "step": 4048
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.0916878879070282,
+      "eval_runtime": 284.6865,
+      "eval_samples_per_second": 7.117,
+      "eval_steps_per_second": 0.892,
+      "eval_wer": 4.214896829391042,
+      "step": 4048
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.930009841918945,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 5060
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.09865663200616837,
+      "eval_runtime": 286.2104,
+      "eval_samples_per_second": 7.079,
+      "eval_steps_per_second": 0.887,
+      "eval_wer": 4.638483475926858,
+      "step": 5060
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.15008990466594696,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 6072
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.09895044565200806,
+      "eval_runtime": 288.0034,
+      "eval_samples_per_second": 7.035,
+      "eval_steps_per_second": 0.882,
+      "eval_wer": 4.999161214561315,
+      "step": 6072
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.05994468554854393,
+      "learning_rate": 1e-05,
+      "loss": 0.004,
+      "step": 7084
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.10006546229124069,
+      "eval_runtime": 285.4295,
+      "eval_samples_per_second": 7.098,
+      "eval_steps_per_second": 0.89,
+      "eval_wer": 4.172957557456803,
+      "step": 7084
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.015984803438186646,
+      "learning_rate": 1e-05,
+      "loss": 0.0039,
+      "step": 8096
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.10367220640182495,
+      "eval_runtime": 285.9651,
+      "eval_samples_per_second": 7.085,
+      "eval_steps_per_second": 0.888,
+      "eval_wer": 4.663647039087401,
+      "step": 8096
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.4414064586162567,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 9108
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.10489141196012497,
+      "eval_runtime": 284.3163,
+      "eval_samples_per_second": 7.126,
+      "eval_steps_per_second": 0.893,
+      "eval_wer": 4.021976178493541,
+      "step": 9108
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.01772579923272133,
+      "learning_rate": 1e-05,
+      "loss": 0.0024,
+      "step": 10120
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.11083633452653885,
+      "eval_runtime": 285.82,
+      "eval_samples_per_second": 7.088,
+      "eval_steps_per_second": 0.889,
+      "eval_wer": 4.265223955712129,
+      "step": 10120
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.2484708892672e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fe7b6a4fda54fec2fd01d24fcf5f4a31e0a66024e607fbbda0272972cf0b9d
+size 5368