egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py
@@ -18,7 +18,7 @@ os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id) inference_pipline = pipeline( task=Tasks.auto_speech_recognition, model="damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch", model="damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k", output_dir=output_dir_job, ) audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
