Training in progress, step 1200

added_tokens.json

@@ -0,0 +1,4 @@
+{
+ "</s>": 56,
+ "<s>": 55
+}

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+ "_name_or_path": "/mnt/models/wav2vec2-common_voice-fr/",
  "activation_dropout": 0.0,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761794badbfa9854c29c9028199d9c56d2c8f33cff29e0fa62820799fa842359
+oid sha256:29970c598012e2661aa7fdc9f00a3b81564b0fbfe198e92e15973d4ab37412c4
 size 1262135533

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>",
+ "do_lower_case": false,
+ "eos_token": "</s>",
+ "model_max_length": 1000000000000000019884624838656,
+ "name_or_path": "/mnt/models/wav2vec2-common_voice-fr",
+ "pad_token": "[PAD]",
+ "replace_word_delimiter_char": " ",
+ "special_tokens_map_file": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba8355dcb356b4d5dbd8efb088b085fbb5bcb58ce9f9d923fa91b2aa7c9d321
+oid sha256:a6d41957ecc5d57800cb66d84db739c0696538779bb418a49d13773142fb08f9
 size 3643

vocab.json

@@ -0,0 +1,57 @@
+{
+ "[PAD]": 54,
+ "[UNK]": 53,
+ "a": 1,
+ "b": 2,
+ "c": 3,
+ "d": 4,
+ "e": 5,
+ "f": 6,
+ "g": 7,
+ "h": 8,
+ "i": 9,
+ "j": 10,
+ "k": 11,
+ "l": 12,
+ "m": 13,
+ "n": 14,
+ "o": 15,
+ "p": 16,
+ "q": 17,
+ "r": 18,
+ "s": 19,
+ "t": 20,
+ "u": 21,
+ "v": 22,
+ "w": 23,
+ "x": 24,
+ "y": 25,
+ "z": 26,
+ "|": 0,
+ "à": 27,
+ "á": 28,
+ "â": 29,
+ "ã": 30,
+ "ç": 31,
+ "è": 32,
+ "é": 33,
+ "ê": 34,
+ "ë": 35,
+ "í": 36,
+ "î": 37,
+ "ï": 38,
+ "ñ": 39,
+ "ò": 40,
+ "ó": 41,
+ "ô": 42,
+ "ö": 43,
+ "ù": 44,
+ "û": 45,
+ "ü": 46,
+ "ÿ": 47,
+ "ń": 48,
+ "ō": 49,
+ "œ": 50,
+ "ū": 51,
+ "’": 52
+}