all)

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 110, "</s>": 111}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "Anas2000/balu",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 109,
+  "proj_codevector_dim": 768,
+  "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": "4.18.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 112,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin → rng_state .pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcca0f8ebd1d036b6ad595b8fc0c2be8905e80385a021cd9ccb72288b1ef9ed9
-size 1262357937
+oid sha256:9dcc64559f12e4179f17053008885e99fde8b048840832e4107e53c403f78352
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7b7d7aabd147995e28cb4a22416db0e4b682b2d0d39de76b312e3c7c3c6e73
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f4d6ee699d0c405d234c5376edd51d0ef5042ddab345524315aa0f85a3c277
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Anas2000/balu", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9242372300308537,
+  "global_step": 4264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "learning_rate": 6.115909912286932e-07,
+      "loss": 1.0478,
+      "step": 328
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.20066721737384796,
+      "eval_runtime": 421.2422,
+      "eval_samples_per_second": 7.122,
+      "eval_steps_per_second": 0.89,
+      "eval_wer": 0.2669276913682244,
+      "step": 328
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.100780032860387e-07,
+      "loss": 1.0471,
+      "step": 656
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.2007066309452057,
+      "eval_runtime": 420.7757,
+      "eval_samples_per_second": 7.13,
+      "eval_steps_per_second": 0.891,
+      "eval_wer": 0.26699953302920365,
+      "step": 656
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.2992075702454e-07,
+      "loss": 1.031,
+      "step": 984
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.20067130029201508,
+      "eval_runtime": 419.7329,
+      "eval_samples_per_second": 7.147,
+      "eval_steps_per_second": 0.893,
+      "eval_wer": 0.266245195588922,
+      "step": 984
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.497635107630415e-07,
+      "loss": 1.044,
+      "step": 1312
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.20047353208065033,
+      "eval_runtime": 419.6669,
+      "eval_samples_per_second": 7.149,
+      "eval_steps_per_second": 0.894,
+      "eval_wer": 0.265885987284026,
+      "step": 1312
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 6.698506463499012e-07,
+      "loss": 1.0448,
+      "step": 1640
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.2001875340938568,
+      "eval_runtime": 423.812,
+      "eval_samples_per_second": 7.079,
+      "eval_steps_per_second": 0.885,
+      "eval_wer": 0.2658141456230468,
+      "step": 1640
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.896934000884026e-07,
+      "loss": 1.0489,
+      "step": 1968
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 0.2000104784965515,
+      "eval_runtime": 432.0862,
+      "eval_samples_per_second": 6.943,
+      "eval_steps_per_second": 0.868,
+      "eval_wer": 0.2658500664535364,
+      "step": 1968
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.09536153826904e-07,
+      "loss": 1.0277,
+      "step": 2296
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.200164794921875,
+      "eval_runtime": 428.8208,
+      "eval_samples_per_second": 6.996,
+      "eval_steps_per_second": 0.874,
+      "eval_wer": 0.26552677897913,
+      "step": 2296
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.2937890756540545e-07,
+      "loss": 1.0364,
+      "step": 2624
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.2002057284116745,
+      "eval_runtime": 426.0723,
+      "eval_samples_per_second": 7.041,
+      "eval_steps_per_second": 0.88,
+      "eval_wer": 0.2659578289450052,
+      "step": 2624
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 3.492216613039069e-07,
+      "loss": 1.035,
+      "step": 2952
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.20034705102443695,
+      "eval_runtime": 425.252,
+      "eval_samples_per_second": 7.055,
+      "eval_steps_per_second": 0.882,
+      "eval_wer": 0.26635295808039083,
+      "step": 2952
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.690644150424083e-07,
+      "loss": 1.0306,
+      "step": 3280
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 0.20014077425003052,
+      "eval_runtime": 418.7166,
+      "eval_samples_per_second": 7.165,
+      "eval_steps_per_second": 0.896,
+      "eval_wer": 0.2662092747584324,
+      "step": 3280
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.8890716878090973e-07,
+      "loss": 1.0395,
+      "step": 3608
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 0.2000894397497177,
+      "eval_runtime": 418.0797,
+      "eval_samples_per_second": 7.176,
+      "eval_steps_per_second": 0.897,
+      "eval_wer": 0.2654908581486404,
+      "step": 3608
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.0874992251941118e-07,
+      "loss": 1.0426,
+      "step": 3936
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.20004504919052124,
+      "eval_runtime": 416.8848,
+      "eval_samples_per_second": 7.196,
+      "eval_steps_per_second": 0.9,
+      "eval_wer": 0.2658141456230468,
+      "step": 3936
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.883705810627083e-08,
+      "loss": 1.0431,
+      "step": 4264
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 0.20020076632499695,
+      "eval_runtime": 419.7762,
+      "eval_samples_per_second": 7.147,
+      "eval_steps_per_second": 0.893,
+      "eval_wer": 0.2656345414705988,
+      "step": 4264
+    }
+  ],
+  "max_steps": 4374,
+  "num_train_epochs": 3,
+  "total_flos": 1.8745213924829307e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1b8ec089881a86b241801da9256eeb50afa541942f7517b88313727fe2d778
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"_": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "“": 27, "”": 28, "œ": 29, "।": 30, "ঁ": 31, "ং": 32, "ঃ": 33, "অ": 34, "আ": 35, "ই": 36, "ঈ": 37, "উ": 38, "ঊ": 39, "ঋ": 40, "এ": 41, "ঐ": 42, "ও": 43, "ঔ": 44, "ক": 45, "খ": 46, "গ": 47, "ঘ": 48, "ঙ": 49, "চ": 50, "ছ": 51, "জ": 52, "ঝ": 53, "ঞ": 54, "ট": 55, "ঠ": 56, "ড": 57, "ঢ": 58, "ণ": 59, "ত": 60, "থ": 61, "দ": 62, "ধ": 63, "ন": 64, "প": 65, "ফ": 66, "ব": 67, "ভ": 68, "ম": 69, "য": 70, "র": 71, "ল": 72, "শ": 73, "ষ": 74, "স": 75, "হ": 76, "়": 77, "া": 78, "ি": 79, "ী": 80, "ু": 81, "ূ": 82, "ৃ": 83, "ে": 84, "ৈ": 85, "ো": 86, "ৌ": 87, "্": 88, "ৎ": 89, "ৗ": 90, "ড়": 91, "ঢ়": 92, "য়": 93, "০": 94, "১": 95, "২": 96, "৩": 97, "৪": 98, "৫": 99, "৬": 100, "৭": 101, "৮": 102, "৯": 103, "ৰ": 104, "‌": 105, "‍": 106, "‎": 107, "|": 0, "[UNK]": 108, "[PAD]": 109}