wav2vec2-xlsr-breton-accent_clf / tokenizer_config.json
alanoix's picture
Training in progress, step 10
dce3198
raw
history blame contribute delete
482 Bytes
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/content/gdrive/MyDrive/02 - bzh_translater/2_SpeechToText/model/wav2vec-xsl-r-300m/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/gdrive/MyDrive/02 - bzh_translater/2_SpeechToText/model/wav2vec-xsl-r-300m", "tokenizer_class": "Wav2Vec2CTCTokenizer"}