| | |
|---|
| | | device = kwargs.get("device", "cuda") |
|---|
| | | if not torch.cuda.is_available() or kwargs.get("ngpu", 0): |
|---|
| | | device = "cpu" |
|---|
| | | # kwargs["batch_size"] = 1 |
|---|
| | | kwargs["batch_size"] = 1 |
|---|
| | | kwargs["device"] = device |
|---|
| | | |
|---|
| | | if kwargs.get("ncpu", None): |
|---|
| | |
|---|
| | | logging.info(f"Loading pretrained params from {init_param}") |
|---|
| | | load_pretrained_model( |
|---|
| | | model=model, |
|---|
| | | init_param=init_param, |
|---|
| | | path=init_param, |
|---|
| | | ignore_init_mismatch=kwargs.get("ignore_init_mismatch", False), |
|---|
| | | oss_bucket=kwargs.get("oss_bucket", None), |
|---|
| | | scope_map=kwargs.get("scope_map", None), |
|---|
| | | excludes=kwargs.get("excludes", None), |
|---|
| | | ) |
|---|
| | | |
|---|
| | | return model, kwargs |
|---|
| | |
|---|
| | | # step.1: compute the vad model |
|---|
| | | self.vad_kwargs.update(cfg) |
|---|
| | | beg_vad = time.time() |
|---|
| | | res = self.generate(input, input_len=input_len, model=self.vad_model, kwargs=self.vad_kwargs, **cfg) |
|---|
| | | res = self.inference(input, input_len=input_len, model=self.vad_model, kwargs=self.vad_kwargs, **cfg) |
|---|
| | | end_vad = time.time() |
|---|
| | | print(f"time cost vad: {end_vad - beg_vad:0.3f}") |
|---|
| | | |
|---|
| | |
|---|
| | | time_speech_total_per_sample = speech_lengths/16000 |
|---|
| | | time_speech_total_all_samples += time_speech_total_per_sample |
|---|
| | | |
|---|
| | | all_segments = [] |
|---|
| | | for j, _ in enumerate(range(0, n)): |
|---|
| | | batch_size_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0]) |
|---|
| | | if j < n - 1 and ( |
|---|
| | |
|---|
| | | batch_size_ms_cum = 0 |
|---|
| | | end_idx = j + 1 |
|---|
| | | speech_j, speech_lengths_j = slice_padding_audio_samples(speech, speech_lengths, sorted_data[beg_idx:end_idx]) |
|---|
| | | results = self.generate(speech_j, input_len=None, model=model, kwargs=kwargs, **cfg) |
|---|
| | | results = self.inference(speech_j, input_len=None, model=model, kwargs=kwargs, **cfg) |
|---|
| | | if self.spk_model is not None: |
|---|
| | | all_segments = [] |
|---|
| | | |
|---|
| | | # compose vad segments: [[start_time_sec, end_time_sec, speech], [...]] |
|---|
| | | for _b in range(len(speech_j)): |
|---|
| | | vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0, \ |
|---|
| | |
|---|
| | | segments = sv_chunk(vad_segments) |
|---|
| | | all_segments.extend(segments) |
|---|
| | | speech_b = [i[2] for i in segments] |
|---|
| | | spk_res = self.generate(speech_b, input_len=None, model=self.spk_model, kwargs=kwargs, **cfg) |
|---|
| | | spk_res = self.inference(speech_b, input_len=None, model=self.spk_model, kwargs=kwargs, **cfg) |
|---|
| | | results[_b]['spk_embedding'] = spk_res[0]['spk_embedding'] |
|---|
| | | beg_idx = end_idx |
|---|
| | | if len(results) < 1: |
|---|
| | |
|---|
| | | # step.3 compute punc model |
|---|
| | | if self.punc_model is not None: |
|---|
| | | self.punc_kwargs.update(cfg) |
|---|
| | | punc_res = self.generate(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg) |
|---|
| | | punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg) |
|---|
| | | result["text_with_punc"] = punc_res[0]["text"] |
|---|
| | | |
|---|
| | | # speaker embedding cluster after resorted |
|---|
