fix contextualparaformer bias_embed

北念

2023-03-29 2b2653ae2b75d18c1d0f994072485bc403374f43

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

@@ -19,7 +19,7 @@
    inference_pipline = pipeline(
        task=Tasks.auto_speech_recognition,
       model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
        model_revision='v1.0.0',
        model_revision='v3.0.0',
        output_dir=output_dir_job,
        batch_size=1,
    )