Training in progress, step 400

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 140, "</s>": 141}

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "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,
+  "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_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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 139,
+  "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": 142,
+  "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 sha256:917141a29ab559d537d6504f810d0e188d68aea8c0d11faf21c863c88d4d8575
+size 1262505841

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": "../robust-asr-italian", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b79d7de43fc2d318cf10cb0fd3f0a51d6135f75e4220295c3e09ecb71abfc13
+size 3055

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, "µ": 39, "»": 40, "ß": 41, "à": 42, "á": 43, "ã": 44, "ä": 45, "å": 46, "æ": 47, "è": 48, "é": 49, "ê": 50, "ë": 51, "ì": 52, "í": 53, "î": 54, "ï": 55, "ð": 56, "ñ": 57, "ò": 58, "ó": 59, "ô": 60, "ö": 61, "ø": 62, "ù": 63, "ú": 64, "û": 65, "ü": 66, "þ": 67, "ÿ": 68, "ā": 69, "ć": 70, "č": 71, "đ": 72, "ė": 73, "ę": 74, "ě": 75, "ğ": 76, "ī": 77, "ı": 78, "ľ": 79, "ł": 80, "ń": 81, "ň": 82, "ō": 83, "ő": 84, "œ": 85, "ř": 86, "ś": 87, "ş": 88, "š": 89, "ū": 90, "ź": 91, "ž": 92, "ș": 93, "ț": 94, "ə": 95, "ʹ": 96, "ʻ": 97, "ʼ": 98, "ʾ": 99, "ʿ": 100, "̇": 101, "а": 102, "б": 103, "е": 104, "л": 105, "ц": 106, "ъ": 107, "ё": 108, "љ": 109, "ד": 110, "ה": 111, "ו": 112, "ḥ": 113, "ṛ": 114, "ṣ": 115, "ṭ": 116, "–": 117, "’": 118, "„": 119, "…": 120, "あ": 121, "ア": 122, "カ": 123, "キ": 124, "サ": 125, "ノ": 126, "ン": 127, "ー": 128, "万": 129, "三": 130, "丰": 131, "古": 132, "多": 133, "峰": 134, "張": 135, "旅": 136, "禅": 137, "|": 0, "[UNK]": 138, "[PAD]": 139}