|
|
@@ -123,6 +123,7 @@ parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
|
|
|
get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_qwen_tokenizer
|
|
|
token_path: !ref <qwen_pretrain_path>
|
|
|
skip_special_tokens: True
|
|
|
+ version: cosyvoice3
|
|
|
allowed_special: 'all'
|
|
|
tokenize: !name:cosyvoice.dataset.processor.tokenize
|
|
|
get_tokenizer: !ref <get_tokenizer>
|