| | |
|---|
| | | import string |
|---|
| | | import logging |
|---|
| | | import os.path |
|---|
| | | import numpy as np |
|---|
| | | from tqdm import tqdm |
|---|
| | | from omegaconf import DictConfig, OmegaConf, ListConfig |
|---|
| | | |
|---|
| | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | 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.") |
|---|
| | |
|---|
| | | self.punc_kwargs = punc_kwargs |
|---|
| | | self.spk_model = spk_model |
|---|
| | | self.spk_kwargs = spk_kwargs |
|---|
| | | self.model_path = kwargs.get("model_path", "./") |
|---|
| | | self.model_path = kwargs.get("model_path") |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | def build_model(self, **kwargs): |
|---|
| | |
|---|
| | | for _b in range(len(speech_j)): |
|---|
| | | vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0, |
|---|
| | | sorted_data[beg_idx:end_idx][_b][0][1]/1000.0, |
|---|
| | | speech_j[_b]]] |
|---|
| | | np.array(speech_j[_b])]] |
|---|
| | | segments = sv_chunk(vad_segments) |
|---|
| | | all_segments.extend(segments) |
|---|
| | | speech_b = [i[2] for i in segments] |
|---|
| | |
|---|
| | | if self.punc_model is not None: |
|---|
| | | self.punc_kwargs.update(cfg) |
|---|
| | | punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg) |
|---|
| | | result["text_with_punc"] = punc_res[0]["text"] |
|---|
| | | result["text"] = punc_res[0]["text"] |
|---|
| | | |
|---|
| | | # speaker embedding cluster after resorted |
|---|
| | | if self.spk_model is not None: |
|---|
