mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
BREAKING(setup): prepare for getting rid of ONNX runtime (#1541)
This commit is contained in:
1 parent
e0544b8ce1
commit
2787f123cc
3 files changed
+14
-6
No files matched your search
@@ -10,6 +10,9 @@
|
||||
- feat(utils): add `"soft"` option to `Powerset.to_multilabel`
|
||||
- improve(pipeline): compute `fbank` on GPU when requested
|
||||
- fix(pipeline): fix `AgglomerativeClustering` to honor `num_clusters` when provided
|
||||
- BREAKING(pipeline): rename `WeSpeakerPretrainedSpeakerEmbedding` to `ONNXWeSpeakerPretrainedSpeakerEmbedding`
|
||||
- BREAKING(setup): remove `onnxruntime` dependency.
|
||||
You can still use ONNX `hbredin/wespeaker-voxceleb-resnet34-LM` but you will have to install `onnxruntime` yourself.
|
||||
|
||||
## Version 3.0.1 (2023-09-28)
|
||||
|
||||
|
||||
@@ -386,7 +386,7 @@ class SpeechBrainPretrainedSpeakerEmbedding(BaseInference):
|
||||
return embeddings
|
||||
|
||||
|
||||
class WeSpeakerPretrainedSpeakerEmbedding(BaseInference):
|
||||
class ONNXWeSpeakerPretrainedSpeakerEmbedding(BaseInference):
|
||||
"""Pretrained WeSpeaker speaker embedding
|
||||
|
||||
Parameters
|
||||
@@ -398,7 +398,7 @@ class WeSpeakerPretrainedSpeakerEmbedding(BaseInference):
|
||||
|
||||
Usage
|
||||
-----
|
||||
>>> get_embedding = WeSpeakerPretrainedSpeakerEmbedding("hbredin/wespeaker-voxceleb-resnet34-LM")
|
||||
>>> get_embedding = ONNXWeSpeakerPretrainedSpeakerEmbedding("hbredin/wespeaker-voxceleb-resnet34-LM")
|
||||
>>> assert waveforms.ndim == 3
|
||||
>>> batch_size, num_channels, num_samples = waveforms.shape
|
||||
>>> assert num_channels == 1
|
||||
@@ -418,7 +418,7 @@ class WeSpeakerPretrainedSpeakerEmbedding(BaseInference):
|
||||
):
|
||||
if not ONNX_IS_AVAILABLE:
|
||||
raise ImportError(
|
||||
f"'onnxruntime' must be installed to use '{embedding}' embeddings. "
|
||||
f"'onnxruntime' must be installed to use '{embedding}' embeddings."
|
||||
)
|
||||
|
||||
super().__init__()
|
||||
@@ -745,7 +745,12 @@ def PretrainedSpeakerEmbedding(
|
||||
>>> embeddings = get_embedding(waveforms, masks=masks)
|
||||
"""
|
||||
|
||||
if isinstance(embedding, str) and "speechbrain" in embedding:
|
||||
if isinstance(embedding, str) and "pyannote" in embedding:
|
||||
return PyannoteAudioPretrainedSpeakerEmbedding(
|
||||
embedding, device=device, use_auth_token=use_auth_token
|
||||
)
|
||||
|
||||
elif isinstance(embedding, str) and "speechbrain" in embedding:
|
||||
return SpeechBrainPretrainedSpeakerEmbedding(
|
||||
embedding, device=device, use_auth_token=use_auth_token
|
||||
)
|
||||
@@ -754,9 +759,10 @@ def PretrainedSpeakerEmbedding(
|
||||
return NeMoPretrainedSpeakerEmbedding(embedding, device=device)
|
||||
|
||||
elif isinstance(embedding, str) and "wespeaker" in embedding:
|
||||
return WeSpeakerPretrainedSpeakerEmbedding(embedding, device=device)
|
||||
return ONNXWeSpeakerPretrainedSpeakerEmbedding(embedding, device=device)
|
||||
|
||||
else:
|
||||
# fallback to pyannote in case we are loading a local model
|
||||
return PyannoteAudioPretrainedSpeakerEmbedding(
|
||||
embedding, device=device, use_auth_token=use_auth_token
|
||||
)
|
||||
|
||||
@@ -3,7 +3,6 @@ einops >=0.6.0
|
||||
huggingface_hub >= 0.13.0
|
||||
lightning >= 2.0.1
|
||||
omegaconf >=2.1,<3.0
|
||||
onnxruntime-gpu >= 1.16.0
|
||||
pyannote.core >= 5.0.0
|
||||
pyannote.database >= 5.0.1
|
||||
pyannote.metrics >= 3.2
|
||||
|
||||
Reference in new issue
Block a user