use Wav2Vec2PhonemeCTCTokenizer tokenizer

tokenizer_config.json

@@ -1 +1 @@
-{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./phoneme_bart_base/", "tokenizer_file": null, "tokenizer_class": "BartTokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "word_delimiter_token": " ", "phonemizer_lang": "en-us", "phonemizer_backend": "espeak", "do_lower_case": true, "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_file": "./vocab.json", "name_or_path": "voidful/phoneme_bart_base", "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer"}