End of training

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 62, "</s>": 63}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 28.728288650512695,
+    "eval_runtime": 5.2804,
+    "eval_samples": 112,
+    "eval_samples_per_second": 21.21,
+    "eval_steps_per_second": 2.651,
+    "eval_wer": 1.0,
+    "train_loss": 20.803141874425553,
+    "train_runtime": 35.5064,
+    "train_samples": 537,
+    "train_samples_per_second": 15.124,
+    "train_steps_per_second": 0.479
+}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "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": 62,
+  "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": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 64,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 28.728288650512695,
+    "eval_runtime": 5.2804,
+    "eval_samples": 112,
+    "eval_samples_per_second": 21.21,
+    "eval_steps_per_second": 2.651,
+    "eval_wer": 1.0
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 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:a205e39703d9fe07ca5f4ab248390a2ddb4ad703dd7b6b57a80da48a96056893
+size 1262186097

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}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-large-xls-r-300m-odia", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 20.803141874425553,
+    "train_runtime": 35.5064,
+    "train_samples": 537,
+    "train_samples_per_second": 15.124,
+    "train_steps_per_second": 0.479
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 17,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 17,
+      "total_flos": 8.750541089193984e+16,
+      "train_loss": 20.803141874425553,
+      "train_runtime": 35.5064,
+      "train_samples_per_second": 15.124,
+      "train_steps_per_second": 0.479
+    }
+  ],
+  "max_steps": 17,
+  "num_train_epochs": 1,
+  "total_flos": 8.750541089193984e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f47908b1b303c62a2b3d41fa0250a4072405be0d19d1d6ad4822b3ea1ec6f2
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"|": 0, "।": 2, "ଁ": 3, "ଂ": 4, "ଃ": 5, "ଅ": 6, "ଆ": 7, "ଇ": 8, "ଈ": 9, "ଉ": 10, "ଊ": 11, "ଏ": 12, "ଓ": 13, "କ": 14, "ଖ": 15, "ଗ": 16, "ଘ": 17, "ଙ": 18, "ଚ": 19, "ଛ": 20, "ଜ": 21, "ଝ": 22, "ଞ": 23, "ଟ": 24, "ଠ": 25, "ଡ": 26, "ଢ": 27, "ଣ": 28, "ତ": 29, "ଥ": 30, "ଦ": 31, "ଧ": 32, "ନ": 33, "ପ": 34, "ଫ": 35, "ବ": 36, "ଭ": 37, "ମ": 38, "ଯ": 39, "ର": 40, "ଲ": 41, "ଳ": 42, "ଵ": 43, "ଶ": 44, "ଷ": 45, "ସ": 46, "ହ": 47, "଼": 48, "ା": 49, "ି": 50, "ୀ": 51, "ୁ": 52, "ୂ": 53, "ୃ": 54, "େ": 55, "ୈ": 56, "ୋ": 57, "ୌ": 58, "୍": 59, "ୟ": 60, "ୱ": 61, "[UNK]": 61, "[PAD]": 62}