Skip to content

Commit

Permalink
fix: fix WeSpeakerPretrainedSpeakerEmbedding GPU support (#1478)
Browse files Browse the repository at this point in the history
  • Loading branch information
hbredin authored Sep 28, 2023
1 parent db24eb6 commit e478d57
Show file tree
Hide file tree
Showing 4 changed files with 14 additions and 3 deletions.
4 changes: 4 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,9 @@
# Changelog

## Version 3.0.1 (2023-09-28)

- fix(pipeline): fix WeSpeaker GPU support

## Version 3.0.0 (2023-09-26)

### Features and improvements
Expand Down
9 changes: 8 additions & 1 deletion pyannote/audio/pipelines/speaker_verification.py
Original file line number Diff line number Diff line change
Expand Up @@ -447,7 +447,14 @@ def to(self, device: torch.device):
if device.type == "cpu":
providers = ["CPUExecutionProvider"]
elif device.type == "cuda":
providers = ["CUDAExecutionProvider"]
providers = [
(
"CUDAExecutionProvider",
{
"cudnn_conv_algo_search": "DEFAULT", # EXHAUSTIVE / HEURISTIC / DEFAULT
},
)
]
else:
warnings.warn(
f"Unsupported device type: {device.type}, falling back to CPU"
Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ einops >=0.6.0
huggingface_hub >= 0.13.0
lightning >= 2.0.1
omegaconf >=2.1,<3.0
onnxruntime >= 1.16.0
onnxruntime-gpu >= 1.16.0
pyannote.core >= 5.0.0
pyannote.database >= 5.0.1
pyannote.metrics >= 3.2
Expand Down
2 changes: 1 addition & 1 deletion version.txt
Original file line number Diff line number Diff line change
@@ -1 +1 @@
3.0.0
3.0.1

0 comments on commit e478d57

Please sign in to comment.