| | |
|---|
| | | ): # download url to local file |
|---|
| | | data_or_path_or_list = download_from_url(data_or_path_or_list) |
|---|
| | | |
|---|
| | | if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file |
|---|
| | | if (isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list)) or hasattr(data_or_path_or_list, 'read'): # local file or bytes io |
|---|
| | | if data_type is None or data_type == "sound": |
|---|
| | | if hasattr(data_or_path_or_list, "read") and hasattr(data_or_path_or_list, "seek"): |
|---|
| | | data_or_path_or_list.seek(0) |
|---|
| | | # if use_ffmpeg: |
|---|
| | | # data_or_path_or_list = _load_audio_ffmpeg(data_or_path_or_list, sr=fs) |
|---|
| | | # data_or_path_or_list = torch.from_numpy(data_or_path_or_list).squeeze() # [n_samples,] |
|---|
| | |
|---|
| | | data_or_path_or_list |
|---|
| | | ).squeeze() # [n_samples,] |
|---|
| | | elif data_type == "text" and tokenizer is not None: |
|---|
| | | data_or_path_or_list = tokenizer.encode(data_or_path_or_list) |
|---|
| | | with open(data_or_path_or_list, "r") as f: |
|---|
| | | data_or_path_or_list = tokenizer.encode(f.read().strip()) |
|---|
| | | elif data_type == "image": # undo |
|---|
| | | pass |
|---|
| | | elif data_type == "video": # undo |
|---|
| | |
|---|
| | | # This launches a subprocess to decode audio while down-mixing |
|---|
| | | # and resampling as necessary. Requires the ffmpeg CLI in PATH. |
|---|
| | | # fmt: off |
|---|
| | | pcm_params = [] |
|---|
| | | if file.lower().endswith('.pcm'): |
|---|
| | | pcm_params = [ |
|---|
| | | "-f", "s16le", |
|---|
| | | "-ar", str(sr), |
|---|
| | | "-ac", "1" |
|---|
| | | ] |
|---|
| | | |
|---|
| | | cmd = [ |
|---|
| | | "ffmpeg", |
|---|
| | | "-nostdin", |
|---|
| | | "-threads", "0", |
|---|
| | | *pcm_params, # PCM files need input format specified before -i since PCM is raw data without headers |
|---|
| | | "-i", file, |
|---|
| | | "-f", "s16le", |
|---|
| | | "-ac", "1", |
|---|
