Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 66,
+  "<s>": 65
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 71,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 74,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81aad00981aa2c3172820b69f4eb43290456850c3ec974b6d5bcb8ef0d7715ca
+size 2423117960

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1cce0157d3c7e75766959dff661de387c5c6c1f3b83d17035e039d6f25fcb1
+size 4846696682

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5226a7b6402d77283255ad91bd9fe2de7cdcfee7d94e0accedbb31a8e9a0a4c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5af39eb138fbe679393389dfca31a0be1e74ccceefd5383e57f616c1a0d126
+size 1064

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "63": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.7127555988315482,
+  "best_model_checkpoint": "whisper-reg-ben\\checkpoint-6000",
+  "epoch": 3.634161114476075,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.30284675953967294,
+      "eval_cer": 0.49007230153778397,
+      "eval_loss": 2.5224013328552246,
+      "eval_runtime": 19.2778,
+      "eval_samples_per_second": 6.951,
+      "eval_steps_per_second": 1.764,
+      "eval_wer": 1.0074001947419668,
+      "step": 500
+    },
+    {
+      "epoch": 0.6056935190793459,
+      "grad_norm": 6.7337727546691895,
+      "learning_rate": 9.692067457838851e-06,
+      "loss": 2.9581,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6056935190793459,
+      "eval_cer": 0.3797115278746284,
+      "eval_loss": 1.7524603605270386,
+      "eval_runtime": 19.6842,
+      "eval_samples_per_second": 6.807,
+      "eval_steps_per_second": 1.727,
+      "eval_wer": 0.84634858812074,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9085402786190188,
+      "eval_cer": 0.3615076889198811,
+      "eval_loss": 1.5823218822479248,
+      "eval_runtime": 18.1939,
+      "eval_samples_per_second": 7.365,
+      "eval_steps_per_second": 1.869,
+      "eval_wer": 0.7945472249269717,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2113870381586918,
+      "grad_norm": 4.9313130378723145,
+      "learning_rate": 9.067457838850719e-06,
+      "loss": 1.6132,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2113870381586918,
+      "eval_cer": 0.3612507799023746,
+      "eval_loss": 1.4997178316116333,
+      "eval_runtime": 21.2924,
+      "eval_samples_per_second": 6.293,
+      "eval_steps_per_second": 1.597,
+      "eval_wer": 0.7700097370983447,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5142337976983646,
+      "eval_cer": 0.36807721951040484,
+      "eval_loss": 1.4603444337844849,
+      "eval_runtime": 17.7387,
+      "eval_samples_per_second": 7.554,
+      "eval_steps_per_second": 1.917,
+      "eval_wer": 0.7518987341772152,
+      "step": 2500
+    },
+    {
+      "epoch": 1.8170805572380375,
+      "grad_norm": 5.206490516662598,
+      "learning_rate": 8.443472829481576e-06,
+      "loss": 1.5051,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8170805572380375,
+      "eval_cer": 0.33611039747495136,
+      "eval_loss": 1.4466902017593384,
+      "eval_runtime": 19.3549,
+      "eval_samples_per_second": 6.923,
+      "eval_steps_per_second": 1.757,
+      "eval_wer": 0.7450827653359299,
+      "step": 3000
+    },
+    {
+      "epoch": 2.1199273167777104,
+      "eval_cer": 0.33500935882849486,
+      "eval_loss": 1.4404141902923584,
+      "eval_runtime": 18.1487,
+      "eval_samples_per_second": 7.383,
+      "eval_steps_per_second": 1.873,
+      "eval_wer": 0.7489776046738073,
+      "step": 3500
+    },
+    {
+      "epoch": 2.4227740763173835,
+      "grad_norm": 4.5190887451171875,
+      "learning_rate": 7.820737039350407e-06,
+      "loss": 1.3798,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4227740763173835,
+      "eval_cer": 0.3345689433699123,
+      "eval_loss": 1.394412636756897,
+      "eval_runtime": 19.6972,
+      "eval_samples_per_second": 6.803,
+      "eval_steps_per_second": 1.726,
+      "eval_wer": 0.7226874391431354,
+      "step": 4000
+    },
+    {
+      "epoch": 2.725620835857056,
+      "eval_cer": 0.3381656696150035,
+      "eval_loss": 1.421527624130249,
+      "eval_runtime": 18.6951,
+      "eval_samples_per_second": 7.168,
+      "eval_steps_per_second": 1.819,
+      "eval_wer": 0.7626095423563778,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0284675953967293,
+      "grad_norm": 12.196548461914062,
+      "learning_rate": 7.196127420362275e-06,
+      "loss": 1.3506,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0284675953967293,
+      "eval_cer": 0.32873343854369286,
+      "eval_loss": 1.3746217489242554,
+      "eval_runtime": 17.0045,
+      "eval_samples_per_second": 7.88,
+      "eval_steps_per_second": 1.999,
+      "eval_wer": 0.7302823758519961,
+      "step": 5000
+    },
+    {
+      "epoch": 3.331314354936402,
+      "eval_cer": 0.3210628693067127,
+      "eval_loss": 1.3873779773712158,
+      "eval_runtime": 19.6904,
+      "eval_samples_per_second": 6.805,
+      "eval_steps_per_second": 1.727,
+      "eval_wer": 0.7230769230769231,
+      "step": 5500
+    },
+    {
+      "epoch": 3.634161114476075,
+      "grad_norm": 5.505178451538086,
+      "learning_rate": 6.57214241099313e-06,
+      "loss": 1.2704,
+      "step": 6000
+    },
+    {
+      "epoch": 3.634161114476075,
+      "eval_cer": 0.31680551987374755,
+      "eval_loss": 1.403659462928772,
+      "eval_runtime": 17.1479,
+      "eval_samples_per_second": 7.814,
+      "eval_steps_per_second": 1.983,
+      "eval_wer": 0.7127555988315482,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 16510,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7849349072039633e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b967ba4ed0328c5cab4ad9d3cb082f89582de82a4ba189f7c3dc275ec6fe76
+size 5432

vocab.json

@@ -0,0 +1,67 @@
+{
+  "[PAD]": 64,
+  "[UNK]": 63,
+  "|": 0,
+  "ঁ": 1,
+  "ং": 2,
+  "ঃ": 3,
+  "অ": 4,
+  "আ": 5,
+  "ই": 6,
+  "ঈ": 7,
+  "উ": 8,
+  "ঊ": 9,
+  "ঋ": 10,
+  "এ": 11,
+  "ঐ": 12,
+  "ও": 13,
+  "ঔ": 14,
+  "ক": 15,
+  "খ": 16,
+  "গ": 17,
+  "ঘ": 18,
+  "ঙ": 19,
+  "চ": 20,
+  "ছ": 21,
+  "জ": 22,
+  "ঝ": 23,
+  "ঞ": 24,
+  "ট": 25,
+  "ঠ": 26,
+  "ড": 27,
+  "ঢ": 28,
+  "ণ": 29,
+  "ত": 30,
+  "থ": 31,
+  "দ": 32,
+  "ধ": 33,
+  "ন": 34,
+  "প": 35,
+  "ফ": 36,
+  "ব": 37,
+  "ভ": 38,
+  "ম": 39,
+  "য": 40,
+  "র": 41,
+  "ল": 42,
+  "শ": 43,
+  "ষ": 44,
+  "স": 45,
+  "হ": 46,
+  "া": 47,
+  "ি": 48,
+  "ী": 49,
+  "ু": 50,
+  "ূ": 51,
+  "ৃ": 52,
+  "ে": 53,
+  "ৈ": 54,
+  "ো": 55,
+  "ৌ": 56,
+  "্": 57,
+  "ৎ": 58,
+  "ড়": 59,
+  "ঢ়": 60,
+  "য়": 61,
+  "‍": 62
+}