fixed token_int is zero bug and add more puncs to sentence

dingbig

2023-03-21 d80d04636547c269ee98c1505e27bf5e1b434c52

 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py

@@ -18,8 +18,8 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
        task=Tasks.auto_speech_recognition,
       model='yufan6/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
        model_revision='v2.0.0',
       model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
        model_revision='v3.0.0',
        output_dir=output_dir_job,
        batch_size=1,
    )