| | |
|---|
| | | def __init__(self, model_dir: Union[str, Path] = None, |
|---|
| | | batch_size: int = 1, |
|---|
| | | device_id: Union[str, int] = "-1", |
|---|
| | | plot_timestamp: bool = False, |
|---|
| | | plot_timestamp_to: str = "", |
|---|
| | | pred_bias: int = 1, |
|---|
| | | quantize: bool = False, |
|---|
| | | intra_op_num_threads: int = 4, |
|---|
| | | ): |
|---|
| | | |
|---|
| | | if not Path(model_dir).exists(): |
|---|
| | | raise FileNotFoundError(f'{model_dir} does not exist.') |
|---|
| | | |
|---|
| | | model_file = os.path.join(model_dir, 'model.onnx') |
|---|
| | | if quantize: |
|---|
| | | model_file = os.path.join(model_dir, 'model_quant.onnx') |
|---|
| | | config_file = os.path.join(model_dir, 'config.yaml') |
|---|
| | | cmvn_file = os.path.join(model_dir, 'am.mvn') |
|---|
| | | config = read_yaml(config_file) |
|---|
| | |
|---|
| | | cmvn_file=cmvn_file, |
|---|
| | | **config['frontend_conf'] |
|---|
| | | ) |
|---|
| | | self.ort_infer = OrtInferSession(model_file, device_id) |
|---|
| | | self.ort_infer = OrtInferSession(model_file, device_id, intra_op_num_threads=intra_op_num_threads) |
|---|
| | | self.batch_size = batch_size |
|---|
| | | self.plot = plot_timestamp |
|---|
| | | self.plot_timestamp_to = plot_timestamp_to |
|---|
| | | self.pred_bias = pred_bias |
|---|
| | | |
|---|
| | | def __call__(self, wav_content: Union[str, np.ndarray, List[str]], **kwargs) -> List: |
|---|
| | | waveform_list = self.load_data(wav_content, self.frontend.opts.frame_opts.samp_freq) |
|---|
| | | waveform_nums = len(waveform_list) |
|---|
| | | asr_res = [] |
|---|
| | | for beg_idx in range(0, waveform_nums, self.batch_size): |
|---|
| | | res = {} |
|---|
| | | |
|---|
| | | end_idx = min(waveform_nums, beg_idx + self.batch_size) |
|---|
| | | feats, feats_len = self.extract_feat(waveform_list[beg_idx:end_idx]) |
|---|
| | | try: |
|---|
| | |
|---|
| | | logging.warning("input wav is silence or noise") |
|---|
| | | preds = [''] |
|---|
| | | else: |
|---|
| | | preds, raw_token = self.decode(am_scores, valid_token_lens)[0] |
|---|
| | | res['preds'] = preds |
|---|
| | | if us_cif_peak is not None: |
|---|
| | | timestamp, timestamp_total = time_stamp_lfr6_onnx(us_cif_peak, copy.copy(raw_token)) |
|---|
| | | res['timestamp'] = timestamp |
|---|
| | | if self.plot: |
|---|
| | | self.plot_wave_timestamp(waveform_list[0], timestamp_total) |
|---|
| | | asr_res.append(res) |
|---|
| | | preds = self.decode(am_scores, valid_token_lens) |
|---|
| | | if us_cif_peak is None: |
|---|
| | | for pred in preds: |
|---|
| | | asr_res.append({'preds': pred}) |
|---|
| | | else: |
|---|
| | | for pred, us_cif_peak_ in zip(preds, us_cif_peak): |
|---|
| | | text, tokens = pred |
|---|
| | | timestamp, timestamp_total = time_stamp_lfr6_onnx(us_cif_peak_, copy.copy(tokens)) |
|---|
| | | if len(self.plot_timestamp_to): |
|---|
| | | self.plot_wave_timestamp(waveform_list[0], timestamp_total, self.plot_timestamp_to) |
|---|
| | | asr_res.append({'preds': text, 'timestamp': timestamp}) |
|---|
| | | return asr_res |
|---|
| | | |
|---|
| | | def plot_wave_timestamp(self, wav, text_timestamp): |
|---|
| | | def plot_wave_timestamp(self, wav, text_timestamp, dest): |
|---|
| | | # TODO: Plot the wav and timestamp results with matplotlib |
|---|
| | | import matplotlib |
|---|
| | | matplotlib.use('Agg') |
|---|
| | |
|---|
| | | x_adj = 0.045 if char != '<sil>' else 0.12 |
|---|
| | | ax1.text((start + end) * 0.5 - x_adj, 0, char) |
|---|
| | | # plt.legend() |
|---|
| | | plotname = "funasr/runtime/python/onnxruntime/debug.png" |
|---|
| | | plotname = "{}/timestamp.png".format(dest) |
|---|
| | | plt.savefig(plotname, bbox_inches='tight') |
|---|
| | | |
|---|
| | | def load_data(self, |
|---|
| | |
|---|
| | | |
|---|
| | | # Change integer-ids to tokens |
|---|
| | | token = self.converter.ids2tokens(token_int) |
|---|
| | | # token = token[:valid_token_num-1] |
|---|
| | | token = token[:valid_token_num-self.pred_bias] |
|---|
| | | texts = sentence_postprocess(token) |
|---|
| | | text = texts[0] |
|---|
| | | # text = self.tokenizer.tokens2text(token) |
|---|
| | | return text, token |
|---|
| | | return texts |
|---|
| | | |
|---|
