Merge pull request #1280 from alibaba-damo-academy/dev_device

Shi Xian

2024-01-22 86dd3ebed46fe572839998ef5229146fefd07a78

Merge pull request #1280 from alibaba-damo-academy/dev_device

Dev device

 funasr/auto/auto_model.py

@@ -97,7 +97,7 @@
        vad_kwargs = kwargs.get("vad_model_revision", None)
        if vad_model is not None:
            logging.info("Building VAD model.")
            vad_kwargs = {"model": vad_model, "model_revision": vad_kwargs}
            vad_kwargs = {"model": vad_model, "model_revision": vad_kwargs, "device": kwargs["device"]}
            vad_model, vad_kwargs = self.build_model(**vad_kwargs)

        # if punc_model is not None, build punc model else None
@@ -105,7 +105,7 @@
        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_kwargs = {"model": punc_model, "model_revision": punc_kwargs, "device": kwargs["device"]}
            punc_model, punc_kwargs = self.build_model(**punc_kwargs)

        # if spk_model is not None, build spk model else None
@@ -113,9 +113,9 @@
        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_kwargs = {"model": spk_model, "model_revision": spk_kwargs, "device": kwargs["device"]}
            spk_model, spk_kwargs = self.build_model(**spk_kwargs)
            self.cb_model = ClusterBackend()
            self.cb_model = ClusterBackend().to(kwargs["device"])
            spk_mode = kwargs.get("spk_mode", 'punc_segment')
            if spk_mode not in ["default", "vad_segment", "punc_segment"]:
                logging.error("spk_mode should be one of default, vad_segment and punc_segment.")
@@ -398,7 +398,7 @@
            if self.spk_model is not None:
                all_segments = sorted(all_segments, key=lambda x: x[0])
                spk_embedding = result['spk_embedding']
                labels = self.cb_model(spk_embedding, oracle_num=self.preset_spk_num)
                labels = self.cb_model(spk_embedding.cpu(), oracle_num=self.preset_spk_num)
                del result['spk_embedding']
                sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
                if self.spk_mode == 'vad_segment':
@@ -406,12 +406,12 @@
                    for res, vadsegment in zip(restored_data, vadsegments):
                        sentence_list.append({"start": vadsegment[0],\
                                                "end": vadsegment[1],
                                                "sentence": res['text'],
                                                "sentence": res['raw_text'],
                                                "timestamp": res['timestamp']})
                else: # punc_segment
                    sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
                                                        result['timestamp'], \
                                                        result['text'])
                                                        result['raw_text'])
                distribute_spk(sentence_list, sv_output)
                result['sentence_info'] = sentence_list
                    

 funasr/models/seaco_paraformer/model.py

@@ -415,12 +415,12 @@
                        token, timestamp)

                    result_i = {"key": key[i], "text": text_postprocessed,
                                "timestamp": time_stamp_postprocessed,
                                "timestamp": time_stamp_postprocessed, "raw_text": copy.copy(text_postprocessed)
                                }
                    
                    if ibest_writer is not None:
                        ibest_writer["token"][key[i]] = " ".join(token)
                        # ibest_writer["text"][key[i]] = text
                        # ibest_writer["raw_text"][key[i]] = text
                        ibest_writer["timestamp"][key[i]] = time_stamp_postprocessed
                        ibest_writer["text"][key[i]] = text_postprocessed
                else: