Load single audio, supports file path or (wav, sr) tuple Args: audio_input: String (file path) or tuple (wav, sr) Returns: tuple: (wav, sr)
(audio_input)
| 220 | |
| 221 | |
| 222 | def _load_single_audio(audio_input): |
| 223 | """Load single audio, supports file path or (wav, sr) tuple |
| 224 | |
| 225 | Args: |
| 226 | audio_input: String (file path) or tuple (wav, sr) |
| 227 | |
| 228 | Returns: |
| 229 | tuple: (wav, sr) |
| 230 | """ |
| 231 | if isinstance(audio_input, tuple) and len(audio_input) == 2: |
| 232 | # Already a (wav, sr) tuple |
| 233 | wav, sr = audio_input |
| 234 | return wav, sr |
| 235 | elif isinstance(audio_input, str): |
| 236 | # Is a file path, needs to be loaded |
| 237 | wav, sr = torchaudio.load(audio_input) |
| 238 | return wav, sr |
| 239 | else: |
| 240 | raise ValueError(f"Unsupported audio input format: {type(audio_input)}") |
| 241 | |
| 242 | |
| 243 | def merge_speaker_audios(wav1, sr1, wav2, sr2, target_sample_rate=16000): |