End of training

.gitignore

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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 83,
+  "<s>": 82
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "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,
+  "gradient_checkpointing": false,
+  "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": 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,
+  "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": 81,
+  "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": "4.29.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 84,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d63c777d4f743fac1322f71cb3ac9aec38e33b7951623cc4d43c0adf37b65b
+size 1262246253

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060d584d1d99701171e63594ddf53e363c4e8b9bfb2b60a189c9f912b54c2f03
+size 3899

vocab.json

@@ -0,0 +1,84 @@
+{
+  "!": 1,
+  "'": 2,
+  ",": 3,
+  "-": 4,
+  ".": 5,
+  ":": 6,
+  ";": 7,
+  "[PAD]": 81,
+  "[UNK]": 80,
+  "|": 0,
+  "ം": 8,
+  "ഃ": 9,
+  "അ": 10,
+  "ആ": 11,
+  "ഇ": 12,
+  "ഈ": 13,
+  "ഉ": 14,
+  "ഊ": 15,
+  "ഋ": 16,
+  "എ": 17,
+  "ഏ": 18,
+  "ഐ": 19,
+  "ഒ": 20,
+  "ഓ": 21,
+  "ഔ": 22,
+  "ക": 23,
+  "ഖ": 24,
+  "ഗ": 25,
+  "ഘ": 26,
+  "ങ": 27,
+  "ച": 28,
+  "ഛ": 29,
+  "ജ": 30,
+  "ഝ": 31,
+  "ഞ": 32,
+  "ട": 33,
+  "ഠ": 34,
+  "ഡ": 35,
+  "ഢ": 36,
+  "ണ": 37,
+  "ത": 38,
+  "ഥ": 39,
+  "ദ": 40,
+  "ധ": 41,
+  "ന": 42,
+  "പ": 43,
+  "ഫ": 44,
+  "ബ": 45,
+  "ഭ": 46,
+  "മ": 47,
+  "യ": 48,
+  "ര": 49,
+  "റ": 50,
+  "ല": 51,
+  "ള": 52,
+  "ഴ": 53,
+  "വ": 54,
+  "ശ": 55,
+  "ഷ": 56,
+  "സ": 57,
+  "ഹ": 58,
+  "ാ": 59,
+  "ി": 60,
+  "ീ": 61,
+  "ു": 62,
+  "ൂ": 63,
+  "ൃ": 64,
+  "െ": 65,
+  "േ": 66,
+  "ൈ": 67,
+  "ൊ": 68,
+  "ോ": 69,
+  "ൌ": 70,
+  "്": 71,
+  "ൗ": 72,
+  "ൺ": 73,
+  "ൻ": 74,
+  "ർ": 75,
+  "ൽ": 76,
+  "ൾ": 77,
+  "‌": 78,
+  "‍": 79
+}