Training in progress, step 400

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 173, "</s>": 174}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-1b",
+  "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": 1024,
+  "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": true,
+  "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": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 172,
+  "proj_codevector_dim": 1024,
+  "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": 175,
+  "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 sha256:3dd57c40dcb28e05ab7adb3b1e7bf5e5e927a56ed348eebf777fa2c8cf3be061
+size 3851209393

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": "../outputs/wav2vec2-xls-r-1b-italian-cv-ls", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0be5dbb5c22c4b69c85b492c6faec59be1db75a507e862c2272b5fe8436722
+size 3119

vocab.json

@@ -0,0 +1 @@
+{"<": 1, "=": 2, ">": 3, "[": 4, "]": 5, "_": 6, "`": 7, "a": 8, "b": 9, "c": 10, "d": 11, "e": 12, "f": 13, "g": 14, "h": 15, "i": 16, "j": 17, "k": 18, "l": 19, "m": 20, "n": 21, "o": 22, "p": 23, "q": 24, "r": 25, "s": 26, "t": 27, "u": 28, "v": 29, "w": 30, "x": 31, "y": 32, "z": 33, "{": 34, "}": 35, "~": 36, "¡": 37, "«": 38, "°": 39, "´": 40, "µ": 41, "º": 42, "»": 43, "ß": 44, "à": 45, "á": 46, "ã": 47, "ä": 48, "å": 49, "æ": 50, "è": 51, "é": 52, "ê": 53, "ë": 54, "ì": 55, "í": 56, "î": 57, "ï": 58, "ð": 59, "ñ": 60, "ò": 61, "ó": 62, "ô": 63, "ö": 64, "ø": 65, "ù": 66, "ú": 67, "û": 68, "ü": 69, "þ": 70, "ÿ": 71, "ā": 72, "ą": 73, "ć": 74, "č": 75, "đ": 76, "ė": 77, "ę": 78, "ě": 79, "ğ": 80, "ī": 81, "ı": 82, "ľ": 83, "ł": 84, "ń": 85, "ň": 86, "ō": 87, "ő": 88, "œ": 89, "ř": 90, "ś": 91, "ş": 92, "š": 93, "ū": 94, "ŭ": 95, "ź": 96, "ż": 97, "ž": 98, "ș": 99, "ț": 100, "ə": 101, "ʻ": 102, "ʼ": 103, "ʾ": 104, "ʿ": 105, "ː": 106, "̨": 107, "а": 108, "б": 109, "д": 110, "е": 111, "л": 112, "н": 113, "о": 114, "с": 115, "у": 116, "ц": 117, "ё": 118, "љ": 119, "ң": 120, "ד": 121, "ה": 122, "ו": 123, "ة": 124, "ر": 125, "س": 126, "ص": 127, "غ": 128, "ل": 129, "ي": 130, "ḥ": 131, "ṛ": 132, "ṣ": 133, "ṭ": 134, "ễ": 135, "‑": 136, "–": 137, "—": 138, "’": 139, "„": 140, "…": 141, "′": 142, "☆": 143, "あ": 144, "ア": 145, "カ": 146, "キ": 147, "サ": 148, "ザ": 149, "ノ": 150, "フ": 151, "リ": 152, "ン": 153, "・": 154, "ー": 155, "万": 156, "三": 157, "丰": 158, "古": 159, "多": 160, "家": 161, "峰": 162, "張": 163, "旅": 164, "禅": 165, "ꞌ": 166, "심": 167, "악": 168, "음": 169, "중": 170, "|": 0, "[UNK]": 171, "[PAD]": 172}