gigant commited on
Commit
e77f3e1
1 Parent(s): 59a447b

Training in progress, step 1000

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 34, "</s>": 35}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dbcbdf916e6438de3023c7108eb53aeafe205ac6665c90cd75fccb800d1b30c
3
  size 1262071281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f294e523d0972b620c666d49e8610ca9a8225b50edd7ff412c212f3eef577b16
3
  size 1262071281
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1 @@
 
 
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": "./gigant/wav2vec2-ro-300m_01", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f797744b915eccd2e6d8d7752d3dbc9565ddcdab329b12c3f1c25398f6222b07
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7ffa627b29ea27b82a7931cc22a9fb4a091533e719e9390368c2eaf451a89f
3
  size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"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, "â": 27, "î": 28, "ă": 29, "ș": 30, "ț": 31, "|": 0, "[UNK]": 32, "[PAD]": 33}