Initial commit

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 63,
+  "transformers_version": "4.4.0",
+  "vocab_size": 64
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966a65359403ee972c8ef550768ff8340ec75e9a99d3db88c9f75222245a2c72
+size 2490601991

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96689ccac5437002359b284dfebd613ef6ed8deb955897287ea97876de17beb1
+size 1262196247

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31d89640f01a756837032045186e234eceab90dc8ffb5630504f626f9377a52
+size 623

special_tokens_map.json

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

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": "|"}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.6961869618696187,
+  "best_model_checkpoint": "./wav2vec2-large-xlsr-punjabi/checkpoint-4000",
+  "epoch": 500.0,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 125.0,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.5768,
+      "step": 1000
+    },
+    {
+      "epoch": 125.0,
+      "eval_loss": 1.6340935230255127,
+      "eval_runtime": 17.7323,
+      "eval_samples_per_second": 6.542,
+      "eval_wer": 0.7527675276752768,
+      "step": 1000
+    },
+    {
+      "epoch": 250.0,
+      "learning_rate": 0.00015999999999999999,
+      "loss": 0.0382,
+      "step": 2000
+    },
+    {
+      "epoch": 250.0,
+      "eval_loss": 1.7394386529922485,
+      "eval_runtime": 18.4529,
+      "eval_samples_per_second": 6.286,
+      "eval_wer": 0.7343173431734318,
+      "step": 2000
+    },
+    {
+      "epoch": 375.0,
+      "learning_rate": 7.999999999999999e-05,
+      "loss": 0.0171,
+      "step": 3000
+    },
+    {
+      "epoch": 375.0,
+      "eval_loss": 1.8244776725769043,
+      "eval_runtime": 18.1059,
+      "eval_samples_per_second": 6.407,
+      "eval_wer": 0.7011070110701108,
+      "step": 3000
+    },
+    {
+      "epoch": 500.0,
+      "learning_rate": 0.0,
+      "loss": 0.009,
+      "step": 4000
+    },
+    {
+      "epoch": 500.0,
+      "eval_loss": 1.8406387567520142,
+      "eval_runtime": 17.9636,
+      "eval_samples_per_second": 6.458,
+      "eval_wer": 0.6961869618696187,
+      "step": 4000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 500,
+  "total_flos": 2.0368243365690655e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfe66b3e0eec2c4ba178c61b01ad395a63d002a67a457f51e0de6b72163e491
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"ਸ਼": 0, "ਲ਼": 1, "ਈ": 2, "ੜ": 3, "ਫ": 4, "ਔ": 5, "ਗ": 6, "ਫ਼": 7, "ਨ": 8, "ਇ": 9, "ਪ": 10, "ੇ": 11, "ੁ": 12, "ਢ": 13, "ਰ": 14, "ੀ": 15, "ਅ": 16, "ਾ": 17, "ਦ": 18, "ਛ": 19, "ਜ਼": 20, "ੂ": 21, "ੈ": 22, "ਣ": 23, "ਡ": 24, "ਘ": 25, "ਜ": 26, "ਕ": 27, "ਓ": 28, "ਊ": 29, "ਸ": 30, "ਭ": 31, "ਤ": 32, "ਐ": 33, "ਯ": 34, "ਉ": 35, "ਗ਼": 36, "ੱ": 37, "ੰ": 38, "ਚ": 39, "ਧ": 40, "ਹ": 41, "ਂ": 42, "੍": 43, "ਿ": 44, "ਟ": 45, "ੋ": 46, "ਆ": 48, "ਝ": 49, "ਏ": 50, "਼": 51, "ਖ": 52, "ਮ": 53, "ਖ਼": 54, "ਵ": 55, "ਬ": 56, "ਲ": 57, "ੌ": 58, "ਠ": 59, "ਥ": 60, "…": 61, "|": 47, "[UNK]": 62, "[PAD]": 63}