update (debugging)

shixian.shi

2024-01-12 bcb8b0c3cbbdc7b3c246a28b3941a9f4301deac0

update (debugging)

 funasr/bin/inference.py

@@ -115,7 +115,7 @@
        vad_model = kwargs.get("vad_model", None)
        vad_kwargs = kwargs.get("vad_model_revision", None)
        if vad_model is not None:
            print("build vad model")
            logging.info("Building VAD model.")
            vad_kwargs = {"model": vad_model, "model_revision": vad_kwargs}
            vad_model, vad_kwargs = self.build_model(**vad_kwargs)

@@ -123,6 +123,7 @@
        punc_model = kwargs.get("punc_model", None)
        punc_kwargs = kwargs.get("punc_model_revision", None)
        if punc_model is not None:
            logging.info("Building punc model.")
            punc_kwargs = {"model": punc_model, "model_revision": punc_kwargs}
            punc_model, punc_kwargs = self.build_model(**punc_kwargs)

@@ -130,6 +131,7 @@
        spk_model = kwargs.get("spk_model", None)
        spk_kwargs = kwargs.get("spk_model_revision", None)
        if spk_model is not None:
            logging.info("Building SPK model.")
            spk_kwargs = {"model": spk_model, "model_revision": spk_kwargs}
            spk_model, spk_kwargs = self.build_model(**spk_kwargs)
            self.cb_model = ClusterBackend()
@@ -166,6 +168,7 @@
            device = "cpu"
            # kwargs["batch_size"] = 1
        kwargs["device"] = device
        import pdb; pdb.set_trace()
        
        if kwargs.get("ncpu", None):
            torch.set_num_threads(kwargs.get("ncpu"))

 funasr/models/seaco_paraformer/model.py

@@ -337,7 +337,8 @@
        meta_data[
            "batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
        
        speech.to(device=kwargs["device"]), speech_lengths.to(device=kwargs["device"])
        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])

        # hotword
        self.hotword_list = self.generate_hotwords_list(kwargs.get("hotword", None), tokenizer=tokenizer, frontend=frontend)