| examples/industrial_data_pretraining/sense_voice/demo.py | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| funasr/models/paraformer/model.py | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| funasr/version.txt | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
examples/industrial_data_pretraining/sense_voice/demo.py
@@ -17,6 +17,7 @@ "task": ("ASR", "AED", "SER"), "language": "auto", "fp16": True, "gain_event": True, } res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions) funasr/models/paraformer/model.py
@@ -475,6 +475,8 @@ speech = speech.to(device=kwargs["device"]) speech_lengths = speech_lengths.to(device=kwargs["device"]) # Encoder if kwargs.get("fp16", False): speech = speech.half() encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) if isinstance(encoder_out, tuple): encoder_out = encoder_out[0] funasr/version.txt
@@ -1 +1 @@ 1.0.22 1.0.23
