bugfix

游雁

2024-04-15 90bc3ad02eee3745188be3960036ae3e9e746049

bugfix

 examples/industrial_data_pretraining/paraformer/finetune.sh

@@ -10,7 +10,7 @@

## option 1, download model automatically
model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"

model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"

## option 2, download model by git
#local_path_root=${workspace}/modelscope_models

 funasr/models/sense_voice/model.py

@@ -96,9 +96,9 @@
        options = whisper.DecodingOptions(**DecodingOptions)
        
        result = whisper.decode(self.model, speech, options)

        text = f"{result.text}\n"
        results = []
        result_i = {"key": key[0], "text": result.text}
        result_i = {"key": key[0], "text": text}

        results.append(result_i)
    

 funasr/tokenizer/char_tokenizer.py

@@ -93,7 +93,8 @@
    return seg_dict

def seg_tokenize(txt, seg_dict):
    pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
    # pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
    pattern = re.compile(r"([\u4E00-\u9FA5A-Za-z0-9])")
    out_txt = ""
    for word in txt:
        word = word.lower()