| | |
|---|
| | | import numpy as np |
|---|
| | | import torch.distributed as dist |
|---|
| | | import torchaudio |
|---|
| | | import soundfile |
|---|
| | | |
|---|
| | | |
|---|
| | | def filter_wav_text(data_dir, dataset): |
|---|
| | |
|---|
| | | |
|---|
| | | |
|---|
| | | def wav2num_frame(wav_path, frontend_conf): |
|---|
| | | waveform, sampling_rate = torchaudio.load(wav_path) |
|---|
| | | try: |
|---|
| | | waveform, sampling_rate = torchaudio.load(wav_path) |
|---|
| | | except: |
|---|
| | | waveform, sampling_rate = soundfile.read(wav_path) |
|---|
| | | waveform = np.expand_dims(waveform, axis=0) |
|---|
| | | n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"]) |
|---|
| | | feature_dim = frontend_conf["n_mels"] * frontend_conf["lfr_m"] |
|---|
| | | return n_frames, feature_dim |
|---|
