Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 118, "</s>": 119}

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": 117,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 120,
+  "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,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a575cda707e1361ced875e0e36c3873b2cf1e9588b1215aced5cf5c4a20b78
+size 1262415665

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}]}

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": "common6/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35e83bf124281a799353c449431469b9f636307ee4ca8f0652b078fdabe7fd8
+size 2991

vocab.json

@@ -0,0 +1 @@
+{"_": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "k": 11, "m": 12, "n": 13, "o": 14, "p": 15, "q": 16, "r": 17, "s": 18, "t": 19, "u": 20, "y": 21, "z": 22, "«": 23, "»": 24, "ā": 25, "š": 26, "،": 27, "؛": 28, "؟": 29, "ء": 30, "آ": 31, "أ": 32, "ؤ": 33, "ئ": 34, "ا": 35, "ب": 36, "ة": 37, "ت": 38, "ث": 39, "ج": 40, "ح": 41, "خ": 42, "د": 43, "ذ": 44, "ر": 45, "ز": 46, "س": 47, "ش": 48, "ص": 49, "ض": 50, "ط": 51, "ظ": 52, "ع": 53, "غ": 54, "ـ": 55, "ف": 56, "ق": 57, "ك": 58, "ل": 59, "م": 60, "ن": 61, "ه": 62, "و": 63, "ى": 64, "ي": 65, "ً": 66, "ٌ": 67, "َ": 68, "ُ": 69, "ِ": 70, "ّ": 71, "ْ": 72, "ٔ": 73, "٬": 74, "پ": 75, "چ": 76, "ژ": 77, "ک": 78, "گ": 79, "ۀ": 80, "ی": 81, "ے": 82, "ﭘ": 83, "ﮐ": 84, "ﮔ": 85, "ﯽ": 86, "ﯾ": 87, "ﯿ": 88, "ﺍ": 89, "ﺎ": 90, "ﺑ": 91, "ﺒ": 92, "ﺖ": 93, "ﺘ": 94, "ﺧ": 95, "ﺩ": 96, "ﺪ": 97, "ﺭ": 98, "ﺮ": 99, "ﺱ": 100, "ﺴ": 101, "ﺷ": 102, "ﺸ": 103, "ﻀ": 104, "ﻋ": 105, "ﻌ": 106, "ﻟ": 107, "ﻡ": 108, "ﻢ": 109, "ﻤ": 110, "ﻥ": 111, "ﻧ": 112, "ﻪ": 113, "ﻭ": 114, "ﻮ": 115, "|": 0, "[UNK]": 116, "[PAD]": 117}