MingJie_Li

from funasr import AutoModel import time wav_file = "/mnt/data/toolbox_dir/voice_trans/test-file/vad_example.wav" model = AutoModel( model="/mnt/data/toolbox_dir/voice_trans/Whisper-large-v3", vad_model="/mnt/data/toolbox_dir/voice_trans/speech_fsmn_vad_zh-cn-16k-common-pytorch", vad_kwargs={"max_single_segment_time": 30000}, punc_model="/mnt/data/toolbox_dir/voice_trans/punc_ct-transformer_cn-en-common-vocab471067-large", spk_model="/mnt/data/toolbox_dir/voice_trans/speech_campplus_sv_zh-cn_16k-common", device='cuda:2' ) start_time = time.time() res = model.generate( input=wav_file, batch_size_s=300, batch_size=1 )...