diff --git a/CHANGELOG.md b/CHANGELOG.md index 47bec945..6026ea24 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,7 @@ - BREAKING(cli): remove gap-filling optimization (`--optimize`) and `OptimizedMinDurationOff` outputs from the `benchmark` command - BREAKING: require Python 3.11 or newer; Python 3.10 is no longer supported - fix(model): restore `fbank_only` mode in WeSpeaker embedding models +- improve(model): compute WeSpeaker fbank features on MPS instead of falling back to CPU [@Isalia20](https://github.com/Isalia20) - fix(task): avoid training crashes with `spawn`/`forkserver` workers, including Python 3.14's default on Linux, by warning and using `num_workers=0` - fix(pipeline): fix `VBxClustering` crashing when more speakers are requested than there are embeddings to cluster [@MohammadHijjawi97](https://github.com/MohammadHijjawi97) diff --git a/src/pyannote/audio/models/embedding/wespeaker/__init__.py b/src/pyannote/audio/models/embedding/wespeaker/__init__.py index bd245b87..332e1994 100644 --- a/src/pyannote/audio/models/embedding/wespeaker/__init__.py +++ b/src/pyannote/audio/models/embedding/wespeaker/__init__.py @@ -126,12 +126,7 @@ class BaseWeSpeakerResNet(Model): waveforms = waveforms * (1 << 15) - # fall back to CPU for FFT computation when using MPS - # until FFT is fixed in MPS - device = waveforms.device - fft_device = torch.device("cpu") if device.type == "mps" else device - - features = torch.vmap(self._fbank)(waveforms.to(fft_device)).to(device) + features = torch.vmap(self._fbank)(waveforms) # center features with global average if self.hparams.fbank_centering_span is None: