fp16

游雁

2024-06-11 63e60cc43ddab5d28908e5e84e26a0553eb120f8

 funasr/models/llm_asr/model.py

@@ -684,6 +684,13 @@
        # audio encoder
        speech = batch["speech"]
        speech_lengths = batch["speech_lengths"][:, 0]
        # fp16
        if kwargs.get("fp16", False):
            speech = speech.to(torch.float16)
            encoder_out_lens = encoder_out_lens.to(torch.float16)
        elif kwargs.get("bf16", False):
            speech = speech.to(torch.bfloat16)
            encoder_out_lens = encoder_out_lens.to(torch.bfloat16)
        encoder_out, encoder_out_lens = self.audio_encoder(speech.permute(0, 2, 1), speech_lengths)

        # audio_adaptor