abdusah
/

aradia-ctc-data2vec-ft

Automatic Speech Recognition Transformers PyTorch data2vec-audio abdusahmbzuai/arabic_speech_massive_300hrs generated_from_trainer Inference Endpoints

Model card Files Files and versions Community

aradia-ctc-data2vec-ft / tokenizer_config.json

Abdulwahab Sahyoun

Model save

b1b95bb about 2 years ago

raw history blame contribute delete

No virus

379 Bytes

{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "config": null, "tokenizer_type": "data2vec-audio", "special_tokens_map_file": null, "name_or_path": "/l/users/abdulwahab.sahyoun/aradia/aradia-ctc-data2vec-ft", "tokenizer_class": "Wav2Vec2CTCTokenizer"}