Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 216, "</s>": 217}

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": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.3,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.15,
+  "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": 216,
+  "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": 218,
+  "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 sha256:9e0d6798afdc026305a2d41555a4db39993ab4b56bf8fdd6e8777b502b95ff51
+size 1262817457

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": "./xls-r-300m-fr/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb65a6864c6934480b0b74a879e77e35b12180cab3e24b285a5fbfe0e5f117b8
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"'": 1, "(": 2, ")": 3, "*": 4, ".": 5, "/": 6, "1": 7, "2": 8, "=": 9, "C": 10, "E": 11, "N": 12, "Q": 13, "R": 14, "Z": 15, "`": 16, "a": 17, "b": 18, "c": 19, "d": 20, "e": 21, "f": 22, "g": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "p": 32, "q": 33, "r": 34, "s": 35, "t": 36, "u": 37, "v": 38, "w": 39, "x": 40, "y": 41, "z": 42, "{": 43, "|": 0, "}": 45, "~": 46, "§": 47, "«": 48, "®": 49, "°": 50, "±": 51, "·": 52, "»": 53, "×": 54, "ß": 55, "æ": 56, "ç": 57, "ð": 58, "ø": 59, "þ": 60, "đ": 61, "ħ": 62, "ı": 63, "ł": 64, "œ": 65, "ǀ": 66, "ǃ": 67, "ɑ": 68, "ə": 69, "ɨ": 70, "ʉ": 71, "ʔ": 72, "ʻ": 73, "ʼ": 74, "ʽ": 75, "ʾ": 76, "ʿ": 77, "ː": 78, "α": 79, "β": 80, "γ": 81, "δ": 82, "ε": 83, "ζ": 84, "η": 85, "θ": 86, "ι": 87, "κ": 88, "λ": 89, "μ": 90, "ν": 91, "ο": 92, "π": 93, "ρ": 94, "ς": 95, "σ": 96, "τ": 97, "υ": 98, "φ": 99, "χ": 100, "ψ": 101, "ω": 102, "а": 103, "г": 104, "е": 105, "з": 106, "и": 107, "к": 108, "м": 109, "н": 110, "о": 111, "п": 112, "р": 113, "ц": 114, "ч": 115, "э": 116, "я": 117, "є": 118, "і": 119, "ј": 120, "џ": 121, "ҫ": 122, "ӌ": 123, "գ": 124, "զ": 125, "ا": 126, "ب": 127, "ة": 128, "د": 129, "ر": 130, "ل": 131, "م": 132, "ن": 133, "و": 134, "ي": 135, "ᄀ": 136, "ᄆ": 137, "ᄉ": 138, "ᄌ": 139, "ᅡ": 140, "ᅢ": 141, "ᅥ": 142, "ᅩ": 143, "ᅵ": 144, "ᆨ": 145, "ᆷ": 146, "ᆸ": 147, "ᆼ": 148, "ቀ": 149, "ከ": 150, "ወ": 151, "ደ": 152, "ጀ": 153, "‐": 154, "–": 155, "—": 156, "―": 157, "’": 158, "„": 159, "†": 160, "′": 161, "‹": 162, "›": 163, "⁄": 164, "₽": 165, "→": 166, "↔": 167, "∅": 168, "∆": 169, "∈": 170, "−": 171, "∞": 172, "∨": 173, "∼": 174, "≥": 175, "⊨": 176, "⋅": 177, "─": 178, "☉": 179, "ⱅ": 180, "ⱎ": 181, "い": 182, "う": 183, "た": 184, "つ": 185, "の": 186, "ひ": 187, "へ": 188, "ま": 189, "む": 190, "め": 191, "も": 192, "や": 193, "三": 194, "丹": 195, "乃": 196, "京": 197, "保": 198, "北": 199, "厳": 200, "宇": 201, "扬": 202, "文": 203, "星": 204, "术": 205, "杜": 206, "津": 207, "牡": 208, "甌": 209, "美": 210, "西": 211, "貴": 212, "青": 213, "馆": 214, "ꝑ": 215, "[UNK]": 215, "[PAD]": 216}