Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "duytran3112/whisper-sm-vivos",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "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": null,
+  "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": 448,
+  "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,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

last-checkpoint/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "duytran3112/whisper-sm-vivos",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "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": null,
+  "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": 448,
+  "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,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,221 @@
+{
+  "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": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "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_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.31.0"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfae1ce0483ee7d709f85d979ef48ca34acff837cb53b6b0b0b5738dbe80615f
+size 1934161157

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
+}

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d2c8e89b76968dd8da7a9713eae29748d3ac37683f9a4695606aeea8480f2f
+size 967102729

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4654d9957152370ac9eb45d2aa8d04af5e9438ba0e7571164ecc0dbb97b880c8
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90dd2338805bd3a69fa663686537f5e5065d09a0615f56ffc3e4278e4e48b9dd
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,266 @@
+{
+  "best_metric": 123.61493123772102,
+  "best_model_checkpoint": "./whisper-vietnamese-3/checkpoint-1000",
+  "epoch": 7.194244604316546,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 2.8534,
+      "step": 25
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 2.0345,
+      "step": 50
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.46e-06,
+      "loss": 1.4058,
+      "step": 75
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 1.0909,
+      "step": 100
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.46e-06,
+      "loss": 0.889,
+      "step": 125
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.96e-06,
+      "loss": 0.7838,
+      "step": 150
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.46e-06,
+      "loss": 0.7152,
+      "step": 175
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.96e-06,
+      "loss": 0.6819,
+      "step": 200
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.4600000000000005e-06,
+      "loss": 0.6581,
+      "step": 225
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.960000000000001e-06,
+      "loss": 0.6276,
+      "step": 250
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.460000000000001e-06,
+      "loss": 0.6055,
+      "step": 275
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 5.9600000000000005e-06,
+      "loss": 0.5197,
+      "step": 300
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 6.460000000000001e-06,
+      "loss": 0.4698,
+      "step": 325
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 6.96e-06,
+      "loss": 0.4506,
+      "step": 350
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 7.4600000000000006e-06,
+      "loss": 0.427,
+      "step": 375
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.960000000000002e-06,
+      "loss": 0.3566,
+      "step": 400
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 8.46e-06,
+      "loss": 0.3178,
+      "step": 425
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 8.96e-06,
+      "loss": 0.2256,
+      "step": 450
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 9.460000000000001e-06,
+      "loss": 0.2437,
+      "step": 475
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 0.2447,
+      "step": 500
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 9.934285714285715e-06,
+      "loss": 0.2431,
+      "step": 525
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 9.862857142857144e-06,
+      "loss": 0.2328,
+      "step": 550
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 9.791428571428571e-06,
+      "loss": 0.1619,
+      "step": 575
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 9.72e-06,
+      "loss": 0.1336,
+      "step": 600
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 9.648571428571429e-06,
+      "loss": 0.1345,
+      "step": 625
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 9.577142857142858e-06,
+      "loss": 0.1369,
+      "step": 650
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 9.505714285714287e-06,
+      "loss": 0.1368,
+      "step": 675
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 9.434285714285714e-06,
+      "loss": 0.1359,
+      "step": 700
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 9.362857142857143e-06,
+      "loss": 0.0739,
+      "step": 725
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 9.291428571428572e-06,
+      "loss": 0.0754,
+      "step": 750
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 9.220000000000002e-06,
+      "loss": 0.0755,
+      "step": 775
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 9.148571428571429e-06,
+      "loss": 0.0732,
+      "step": 800
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 9.077142857142858e-06,
+      "loss": 0.07,
+      "step": 825
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 9.005714285714287e-06,
+      "loss": 0.0556,
+      "step": 850
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 8.934285714285716e-06,
+      "loss": 0.0374,
+      "step": 875
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 8.862857142857143e-06,
+      "loss": 0.0359,
+      "step": 900
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 8.791428571428572e-06,
+      "loss": 0.0392,
+      "step": 925
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 0.0409,
+      "step": 950
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 8.64857142857143e-06,
+      "loss": 0.0402,
+      "step": 975
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 8.577142857142858e-06,
+      "loss": 0.0204,
+      "step": 1000
+    },
+    {
+      "epoch": 7.19,
+      "eval_cer": 105.08606186100687,
+      "eval_loss": 0.4899536669254303,
+      "eval_runtime": 247.7316,
+      "eval_samples_per_second": 0.997,
+      "eval_steps_per_second": 0.125,
+      "eval_wer": 123.61493123772102,
+      "step": 1000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 29,
+  "total_flos": 4.60322572050432e+18,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23859ad4c36f1f528ab725dd42b5fc2ec1b855a2332883c733b13d2ed717dbba
+size 4091

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d2c8e89b76968dd8da7a9713eae29748d3ac37683f9a4695606aeea8480f2f
+size 967102729

runs/Aug17_16-46-37_8582233f681d/events.out.tfevents.1692290809.8582233f681d.216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009f2e6ffda944e495480f1aae52f4224acf27ead27752075824589e45dbf9bb
+size 11531

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23859ad4c36f1f528ab725dd42b5fc2ec1b855a2332883c733b13d2ed717dbba
+size 4091