| funasr/models/whisper/model.py | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
funasr/models/whisper/model.py
@@ -9,6 +9,7 @@ from torch import nn import whisper # import whisper_timestamped as whisper from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank @@ -111,10 +112,10 @@ # decode the audio options = whisper.DecodingOptions(**kwargs.get("DecodingOptions", {})) result = whisper.decode(self.model, speech, language='english') result = whisper.decode(self.model, speech, options=options) # result = whisper.transcribe(self.model, speech) results = [] result_i = {"key": key[0], "text": result.text}