Merge pull request #672 from alibaba-damo-academy/dev_lhn
bug fix
| | |
|---|
| | | |
|---|
| | | def wav2num_frame(wav_path, frontend_conf): |
|---|
| | | try: |
|---|
| | | waveform, audio_sr = torchaudio.load(wav_file) |
|---|
| | | waveform, sampling_rate = torchaudio.load(wav_path) |
|---|
| | | except: |
|---|
| | | waveform, audio_sr = soundfile.read(wav_file) |
|---|
| | | waveform, sampling_rate = soundfile.read(wav_path) |
|---|
| | | waveform = torch.tensor(np.expand_dims(waveform, axis=0)) |
|---|
| | | speech_length = (waveform.shape[1] / sampling_rate) * 1000. |
|---|
| | | n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"]) |
|---|
