End of training

README.md

@@ -8,24 +8,9 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_11_0
-metrics:
-- wer
 model-index:
 - name: Whisper Small AZ - Balakishiyev Ali
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 11.0
-      type: mozilla-foundation/common_voice_11_0
-      config: az
-      split: None
-      args: 'config: az, split: test'
-    metrics:
-    - name: Wer
-      type: wer
-      value: 57.57575757575758
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,9 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper Small AZ - Balakishiyev Ali
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.1971
-- Wer: 57.5758
 
 ## Model description
 
@@ -62,19 +44,9 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0001        | 250.0  | 1000 | 1.0531          | 53.9394 |
-| 0.0           | 500.0  | 2000 | 1.1288          | 56.3636 |
-| 0.0           | 750.0  | 3000 | 1.1782          | 58.1818 |
-| 0.0           | 1000.0 | 4000 | 1.1971          | 57.5758 |
-
-
 ### Framework versions
 
 - Transformers 4.48.3

checkpoint_1000/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": "4.48.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint_1000/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": "azerbaijani",
+  "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": "4.48.3"
+}

checkpoint_1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcfdbd5edfaa83633b98207153d1e64dc94be44f19cf3ccf269f01a05c8e100
+size 966995080

checkpoint_1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a690fbabb4b1a55d230cdaf45162127f4e259fdbe10909ae71bb33fa87475e5b
+size 1925064044

checkpoint_1000/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
+}

checkpoint_1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7af24fc69f7e10013e9dabc2703b6fe5b38865665686af8c2c2081b8bec9971
+size 14244

checkpoint_1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5101d8c1f86d6f48167e50b1164b9ba363ab76694ff2d5c1e326e3d5f94ecaef
+size 1064

checkpoint_1000/trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": 53.939393939393945,
+  "best_model_checkpoint": "./whisper-small-az/checkpoint-1000",
+  "epoch": 250.0,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.25,
+      "grad_norm": 14.350049018859863,
+      "learning_rate": 4.4e-07,
+      "loss": 1.3755,
+      "step": 25
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 9.423840522766113,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 1.0989,
+      "step": 50
+    },
+    {
+      "epoch": 18.75,
+      "grad_norm": 6.209718704223633,
+      "learning_rate": 1.44e-06,
+      "loss": 0.6302,
+      "step": 75
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 3.1120553016662598,
+      "learning_rate": 1.94e-06,
+      "loss": 0.2227,
+      "step": 100
+    },
+    {
+      "epoch": 31.25,
+      "grad_norm": 0.41890719532966614,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 0.0443,
+      "step": 125
+    },
+    {
+      "epoch": 37.5,
+      "grad_norm": 0.14954017102718353,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 0.0097,
+      "step": 150
+    },
+    {
+      "epoch": 43.75,
+      "grad_norm": 0.08068686723709106,
+      "learning_rate": 3.44e-06,
+      "loss": 0.0046,
+      "step": 175
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.0662764459848404,
+      "learning_rate": 3.94e-06,
+      "loss": 0.003,
+      "step": 200
+    },
+    {
+      "epoch": 56.25,
+      "grad_norm": 0.04160891845822334,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.0021,
+      "step": 225
+    },
+    {
+      "epoch": 62.5,
+      "grad_norm": 0.031241776421666145,
+      "learning_rate": 4.94e-06,
+      "loss": 0.0016,
+      "step": 250
+    },
+    {
+      "epoch": 68.75,
+      "grad_norm": 0.02429639920592308,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 0.0012,
+      "step": 275
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.024689121171832085,
+      "learning_rate": 5.94e-06,
+      "loss": 0.001,
+      "step": 300
+    },
+    {
+      "epoch": 81.25,
+      "grad_norm": 0.014733972027897835,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 0.0008,
+      "step": 325
+    },
+    {
+      "epoch": 87.5,
+      "grad_norm": 0.012692940421402454,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 0.0007,
+      "step": 350
+    },
+    {
+      "epoch": 93.75,
+      "grad_norm": 0.0114270756021142,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 0.0006,
+      "step": 375
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.009990418329834938,
+      "learning_rate": 7.94e-06,
+      "loss": 0.0005,
+      "step": 400
+    },
+    {
+      "epoch": 106.25,
+      "grad_norm": 0.007662411779165268,
+      "learning_rate": 8.44e-06,
+      "loss": 0.0004,
+      "step": 425
+    },
+    {
+      "epoch": 112.5,
+      "grad_norm": 0.006897376384586096,
+      "learning_rate": 8.94e-06,
+      "loss": 0.0004,
+      "step": 450
+    },
+    {
+      "epoch": 118.75,
+      "grad_norm": 0.0064265248365700245,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.0003,
+      "step": 475
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.00633584288880229,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.0003,
+      "step": 500
+    },
+    {
+      "epoch": 131.25,
+      "grad_norm": 0.005206201691180468,
+      "learning_rate": 9.937142857142858e-06,
+      "loss": 0.0002,
+      "step": 525
+    },
+    {
+      "epoch": 137.5,
+      "grad_norm": 0.00430842163041234,
+      "learning_rate": 9.865714285714285e-06,
+      "loss": 0.0002,
+      "step": 550
+    },
+    {
+      "epoch": 143.75,
+      "grad_norm": 0.004347742069512606,
+      "learning_rate": 9.794285714285714e-06,
+      "loss": 0.0002,
+      "step": 575
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.004352904390543699,
+      "learning_rate": 9.722857142857143e-06,
+      "loss": 0.0002,
+      "step": 600
+    },
+    {
+      "epoch": 156.25,
+      "grad_norm": 0.0033592204563319683,
+      "learning_rate": 9.651428571428572e-06,
+      "loss": 0.0002,
+      "step": 625
+    },
+    {
+      "epoch": 162.5,
+      "grad_norm": 0.003341004019603133,
+      "learning_rate": 9.58e-06,
+      "loss": 0.0002,
+      "step": 650
+    },
+    {
+      "epoch": 168.75,
+      "grad_norm": 0.0031617768108844757,
+      "learning_rate": 9.508571428571429e-06,
+      "loss": 0.0001,
+      "step": 675
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.003022307762876153,
+      "learning_rate": 9.437142857142858e-06,
+      "loss": 0.0001,
+      "step": 700
+    },
+    {
+      "epoch": 181.25,
+      "grad_norm": 0.0027644785586744547,
+      "learning_rate": 9.365714285714287e-06,
+      "loss": 0.0001,
+      "step": 725
+    },
+    {
+      "epoch": 187.5,
+      "grad_norm": 0.002608550013974309,
+      "learning_rate": 9.294285714285714e-06,
+      "loss": 0.0001,
+      "step": 750
+    },
+    {
+      "epoch": 193.75,
+      "grad_norm": 0.002360701095312834,
+      "learning_rate": 9.222857142857143e-06,
+      "loss": 0.0001,
+      "step": 775
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.0027755298651754856,
+      "learning_rate": 9.151428571428572e-06,
+      "loss": 0.0001,
+      "step": 800
+    },
+    {
+      "epoch": 206.25,
+      "grad_norm": 0.0021338986698538065,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 0.0001,
+      "step": 825
+    },
+    {
+      "epoch": 212.5,
+      "grad_norm": 0.002221581991761923,
+      "learning_rate": 9.00857142857143e-06,
+      "loss": 0.0001,
+      "step": 850
+    },
+    {
+      "epoch": 218.75,
+      "grad_norm": 0.0020208328496664762,
+      "learning_rate": 8.937142857142857e-06,
+      "loss": 0.0001,
+      "step": 875
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.002234733197838068,
+      "learning_rate": 8.865714285714287e-06,
+      "loss": 0.0001,
+      "step": 900
+    },
+    {
+      "epoch": 231.25,
+      "grad_norm": 0.0017689570086076856,
+      "learning_rate": 8.794285714285716e-06,
+      "loss": 0.0001,
+      "step": 925
+    },
+    {
+      "epoch": 237.5,
+      "grad_norm": 0.001749723101966083,
+      "learning_rate": 8.722857142857145e-06,
+      "loss": 0.0001,
+      "step": 950
+    },
+    {
+      "epoch": 243.75,
+      "grad_norm": 0.0018199320184066892,
+      "learning_rate": 8.651428571428572e-06,
+      "loss": 0.0001,
+      "step": 975
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.0018287795828655362,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 0.0001,
+      "step": 1000
+    },
+    {
+      "epoch": 250.0,
+      "eval_loss": 1.053104043006897,
+      "eval_runtime": 10.8714,
+      "eval_samples_per_second": 2.024,
+      "eval_steps_per_second": 0.276,
+      "eval_wer": 53.939393939393945,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1000,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.25663465472e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint_1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ea7d8d108ea55a58b9ea2db7159df664b15af432bd28d0ed54bf468220391c
+size 5496

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddcfdbd5edfaa83633b98207153d1e64dc94be44f19cf3ccf269f01a05c8e100
+oid sha256:1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596b
 size 966995080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ea7d8d108ea55a58b9ea2db7159df664b15af432bd28d0ed54bf468220391c
+oid sha256:921e97929a5b725179d851e7d5537edc6bf9aaf644d3c7005bfb5194a61e3a2e
 size 5496