mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
Merge branch 'release/4.0.7'
This commit is contained in:
commit
b749285c5c
4 files changed
+60
-31
No files matched your search
+3
-2
@@ -1,8 +1,9 @@
|
||||
# CHANGELOG
|
||||
|
||||
## next
|
||||
## Version 4.0.7 (2026-06-30)
|
||||
|
||||
- improve(pipeline): add support for `subfolder` in `Pipeline.from_pretrained`
|
||||
- fix(pipeline): add missing support for `subfolder` in `Pipeline.from_pretrained`
|
||||
- feat(pipeline): add basic support for (sequential) batch inference
|
||||
|
||||
## Version 4.0.5 (2026-06-22)
|
||||
|
||||
|
||||
@@ -43,6 +43,7 @@ try:
|
||||
import torchcodec
|
||||
from torchcodec import AudioSamples
|
||||
from torchcodec.decoders import AudioDecoder, AudioStreamMetadata
|
||||
TORCHCODEC_AVAILABLE = True
|
||||
except Exception as e:
|
||||
warnings.warn(
|
||||
"\ntorchcodec is not installed correctly so built-in audio decoding will fail. Solutions are:\n"
|
||||
@@ -50,6 +51,9 @@ except Exception as e:
|
||||
"* fix torchcodec installation. Error message was:\n\n"
|
||||
f"{e}"
|
||||
)
|
||||
TORCHCODEC_AVAILABLE = False
|
||||
AudioDecoder = None
|
||||
AudioStreamMetadata = None
|
||||
|
||||
|
||||
AudioFile = str | Path | IOBase | Mapping
|
||||
@@ -81,8 +85,19 @@ def get_audio_metadata(file: AudioFile) -> "AudioStreamMetadata":
|
||||
-------
|
||||
metadata : AudioStreamMetadata
|
||||
Audio file metadata
|
||||
|
||||
Raises
|
||||
------
|
||||
RuntimeError if torchcodec is not available.
|
||||
"""
|
||||
|
||||
if not TORCHCODEC_AVAILABLE:
|
||||
raise RuntimeError(
|
||||
"torchcodec is not available. Cannot read audio metadata. "
|
||||
"Please install torchcodec or provide audio as a waveform dictionary: "
|
||||
"{'waveform': (channel, time) torch.Tensor, 'sample_rate': int}"
|
||||
)
|
||||
|
||||
metadata = AudioDecoder(file["audio"]).metadata
|
||||
|
||||
# rewind if needed
|
||||
@@ -316,6 +331,13 @@ class Audio:
|
||||
|
||||
return self.downmix_and_resample(waveform, sample_rate, channel=channel)
|
||||
|
||||
if not TORCHCODEC_AVAILABLE:
|
||||
raise RuntimeError(
|
||||
"torchcodec is not available. Cannot read audio file. "
|
||||
"Please install torchcodec or provide audio as a waveform dictionary: "
|
||||
"{'waveform': (channel, time) torch.Tensor, 'sample_rate': int}"
|
||||
)
|
||||
|
||||
decoder = AudioDecoder(file["audio"])
|
||||
samples: AudioSamples = decoder.get_all_samples()
|
||||
|
||||
@@ -391,6 +413,13 @@ class Audio:
|
||||
data = F.pad(data, (pad_start, pad_end))
|
||||
return self.downmix_and_resample(data, sample_rate, channel=channel)
|
||||
|
||||
if not TORCHCODEC_AVAILABLE:
|
||||
raise RuntimeError(
|
||||
"torchcodec is not available. Cannot crop audio file. "
|
||||
"Please install torchcodec or provide audio as a waveform dictionary: "
|
||||
"{'waveform': (channel, time) torch.Tensor, 'sample_rate': int}"
|
||||
)
|
||||
|
||||
decoder = AudioDecoder(file["audio"])
|
||||
|
||||
metadata: AudioStreamMetadata = decoder.metadata
|
||||
|
||||
@@ -486,12 +486,33 @@ class Pipeline(_Pipeline):
|
||||
|
||||
return file
|
||||
|
||||
def _apply_batch(
|
||||
self,
|
||||
files: list,
|
||||
**kwargs,
|
||||
) -> Iterator[tuple[Any, Any]]:
|
||||
"""Process a list of prepared files, yielding (file, prediction) pairs"""
|
||||
|
||||
# if pipeline natively supports batch processing, use it
|
||||
if hasattr(self, "apply_batch"):
|
||||
# TODO: warn user that pipeline_kwargs might not be taken into account.
|
||||
for f, prediction in self.apply_batch(files, **kwargs):
|
||||
track_pipeline_apply(self, f, **kwargs)
|
||||
yield f, prediction
|
||||
|
||||
# otherwise process files sequentially
|
||||
else:
|
||||
for f in files:
|
||||
prediction = self.apply(f, **f.get("pipeline_kwargs", {}), **kwargs)
|
||||
track_pipeline_apply(self, f, **kwargs)
|
||||
yield f, prediction
|
||||
|
||||
def __call__(
|
||||
self,
|
||||
file: AudioFile | list[AudioFile],
|
||||
preload: bool = False,
|
||||
**kwargs,
|
||||
) -> Any | Iterator[tuple[str, Any]]:
|
||||
) -> Any | Iterator[tuple[Any, Any]]:
|
||||
"""Validate file(s), (optionally) load it/them in memory, then process it/them
|
||||
|
||||
Parameters
|
||||
@@ -511,13 +532,12 @@ class Pipeline(_Pipeline):
|
||||
Returns (for single file)
|
||||
-------------------------
|
||||
output : Any
|
||||
Whatever `self.apply(...)` returns for a single file, or a dict
|
||||
mapping each URI to its output for batch input.
|
||||
Whatever `self.apply(...)` returns for a single file.
|
||||
|
||||
Yields (for multiple files)
|
||||
Returns (for list of files)
|
||||
---------------------------
|
||||
file : AudioFile
|
||||
output : Any
|
||||
predictions : Iterator[tuple[AudioFile, Any]]
|
||||
Iterator of (file, prediction) pairs.
|
||||
|
||||
"""
|
||||
fix_reproducibility(getattr(self, "device", torch.device("cpu")))
|
||||
@@ -557,28 +577,7 @@ class Pipeline(_Pipeline):
|
||||
f"Duplicate URIs: {duplicates}"
|
||||
)
|
||||
|
||||
# if pipeline natively supports batch processing, use it
|
||||
if hasattr(self, "apply_batch"):
|
||||
# TODO: warn user that pipeline_kwargs might not be taken into account.
|
||||
for f, prediction in self.apply_batch(files, **kwargs):
|
||||
# send file duration to telemetry as well as
|
||||
# requested number of speakers in case of diarization
|
||||
track_pipeline_apply(self, f, **kwargs)
|
||||
|
||||
yield f, prediction
|
||||
|
||||
# otherwise process files sequentially
|
||||
else:
|
||||
for f in files:
|
||||
prediction = self.apply(f, **f.get("pipeline_kwargs", {}), **kwargs)
|
||||
|
||||
# send file duration to telemetry as well as
|
||||
# requested number of speakers in case of diarization
|
||||
track_pipeline_apply(self, f, **kwargs)
|
||||
|
||||
yield f, prediction
|
||||
|
||||
return
|
||||
return self._apply_batch(files, **kwargs)
|
||||
|
||||
file = self.prepare_one(file, preload=preload)
|
||||
prediction = self.apply(file, **file.get("pipeline_kwargs", {}), **kwargs)
|
||||
|
||||
@@ -334,7 +334,7 @@ class Peak:
|
||||
alpha: float = 0.5,
|
||||
min_duration: float = 1.0,
|
||||
):
|
||||
super(Peak, self).__init__()
|
||||
super().__init__()
|
||||
self.alpha = alpha
|
||||
self.min_duration = min_duration
|
||||
|
||||
|
||||
Reference in new issue
Block a user