feat(pyannoteAI): add wrapper around pyannoteAI SDK

This commit is contained in:
Hervé BREDIN authored and GitHub committed 2025-03-14 22:40:52 +01:00
1 parent ce495767be
commit 963b6cf83e
7 files changed
+263 -67

No files matched your search

+12 -3
View File
@@ -4,7 +4,7 @@
### TL;DR
#### Quality of life improvements
#### Quality-of-Life improvements
Models can now be stored alongside their pipelines in the same repository, streamlining gating mechanism:
- accept `pyannote/speaker-diarization-x.x` pipeline user agreement
@@ -12,9 +12,17 @@ Models can now be stored alongside their pipelines in the same repository, strea
- ~~accept `pyannote/wespeaker-voxceleb-resnet34-LM` model user agreement~~
- load pipeline with `Pipeline.from_pretrained("pyannote/speaker-diarization-3.1", token=True)`
#### Improve speech separation quality
#### [pyannoteAI](https://www.pyannote.ai) premium speaker diarization
Clipping and speaker/source alignment issues in speech separation pipeline have been fixed.
Change one line of code to use [pyannoteAI](https://docs.pyannote.ai) and enjoy **more accurate speaker diarization**.
```diff
from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained(
- "pyannote/speaker-diarization-3.1", token="huggingface-access-token")
+ "pyannoteAI/speaker-diarization-precision, token="pyannoteAI-api-key")
diarization = pipeline("/path/to/conversation.wav")
```
### Breaking changes
@@ -31,6 +39,7 @@ Clipping and speaker/source alignment issues in speech separation pipeline have
### New features
- feat(pyannoteAI): add wrapper around pyannoteAI SDK
- improve(hub): add support for pipeline repos that also include underlying models
- feat(clustering): add support for `k-means` clustering
- feat(model): add `wav2vec_frozen` option to freeze/unfreeze `wav2vec` in `SSeRiouSS` architecture
+63 -34
View File
@@ -1,7 +1,7 @@
Using `pyannote.audio` open-source toolkit in production?
Consider switching to [pyannoteAI](https://www.pyannote.ai) for better and faster options.
# `pyannote.audio` speaker diarization toolkit
# `pyannote` speaker diarization toolkit
`pyannote.audio` is an open-source toolkit written in Python for speaker diarization. Based on [PyTorch](https://pytorch.org) machine learning framework, it comes with state-of-the-art [pretrained models and pipelines](https://hf.co/pyannote), that can be further finetuned to your own data for even better performance.
@@ -9,28 +9,38 @@ Consider switching to [pyannoteAI](https://www.pyannote.ai) for better and faste
<a href="https://www.youtube.com/watch?v=37R_R82lfwA"><img src="https://img.youtube.com/vi/37R_R82lfwA/0.jpg"></a>
</p>
## TL;DR
## Highlights
- :exploding_head: state-of-the-art performance (see [Benchmark](#benchmark))
- :hugs: pretrained [pipelines](https://hf.co/models?other=pyannote-audio-pipeline) (and [models](https://hf.co/models?other=pyannote-audio-model)) on [:hugs: model hub](https://huggingface.co/pyannote)
- :rocket: built-in support for [pyannoteAI](https://pyannote.ai) premium speaker diarization
- :snake: Python-first API
- :zap: multi-GPU training with [pytorch-lightning](https://pytorchlightning.ai/)
## Open-source speaker diarization pipeline
1. Install [`pyannote.audio`](https://github.com/pyannote/pyannote-audio) with `pip install pyannote.audio`
2. Accept [`pyannote/segmentation-3.0`](https://hf.co/pyannote/segmentation-3.0) user conditions
3. Accept [`pyannote/speaker-diarization-3.1`](https://hf.co/pyannote/speaker-diarization-3.1) user conditions
4. Create access token at [`hf.co/settings/tokens`](https://hf.co/settings/tokens).
4. Create Huggingface access token at [`hf.co/settings/tokens`](https://hf.co/settings/tokens).
```python
import torch
from pyannote.audio import Pipeline
from pyannote.audio.pipelines.utils.hook import ProgressHook
# Open-source pyannote speaker diarization pipeline
pipeline = Pipeline.from_pretrained(
"pyannote/speaker-diarization-3.1",
token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
token="HUGGINGFACE_ACCESS_TOKEN")
# send pipeline to GPU (when available)
import torch
pipeline.to(torch.device("cuda"))
# apply pretrained pipeline (with optional progress hook)
with ProgressHook() as hook:
diarization = pipeline("audio.wav", hook=hook)
diarization = pipeline("audio.wav", hook=hook) # runs locally
# print the result
for turn, _, speaker in diarization.itertracks(yield_label=True):
@@ -39,14 +49,56 @@ for turn, _, speaker in diarization.itertracks(yield_label=True):
# start=1.8s stop=3.9s speaker_1
# start=4.2s stop=5.7s speaker_0
# ...
```
## Highlights
## Premium pyannoteAI speaker diarization pipeline
1. Install [`pyannote.audio`](https://github.com/pyannote/pyannote-audio) with `pip install pyannote.audio`
2. Create pyannoteAI API key at [`dashboard.pyannote.ai`](https://dashboard.pyannote.ai)
```python
from pyannote.audio import Pipeline
# Premium pyannoteAI speaker diarization service
pipeline = Pipeline.from_pretrained(
"pyannoteAI/speaker-diarization-precision", token="PYANNOTEAI_API_KEY")
diarization = pipeline("audio.wav") # runs on pyannoteAI servers
# print the result
for turn, _, speaker in diarization.itertracks(yield_label=True):
print(f"start={turn.start:.1f}s stop={turn.end:.1f}s {speaker}")
# start=0.2s stop=1.6s SPEAKER_00
# start=1.8s stop=4.0s SPEAKER_01
# start=4.2s stop=5.6s SPEAKER_00
# ...
```
Visit [`docs.pyannote.ai`](https://docs.pyannote.ai) to learn about other pyannoteAI features (voiceprinting, confidence scores, ...)
## Benchmark
Out of the box, `pyannote.audio` speaker diarization [pipeline v3.1](https://hf.co/pyannote/speaker-diarization-3.1) is expected to be much better (and faster) than v2.x. [`pyannoteAI`](https://www.pyannote.ai) premium model goes one step further. Those numbers are diarization error rates (in %) - the lower the better.
| Benchmark (2025-03) | [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) | [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) | <a href="https://docs.pyannote.ai"><img src="https://avatars.githubusercontent.com/u/162698670" width="32" /></a> |
| --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------------------------------------ | ------------------------------------------------ |
| [AISHELL-4](https://arxiv.org/abs/2104.03603) | 14.1 | 12.2 | 12.1 |
| [AliMeeting](https://www.openslr.org/119/) (channel 1) | 27.4 | 24.5 | 19.8 |
| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (IHM) | 18.9 | 18.8 | 15.8 |
| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (SDM) | 27.1 | 22.7 | 18.3 |
| [AVA-AVD](https://arxiv.org/abs/2111.14448) | 66.3 | 49.7 | 45.3 |
| [CALLHOME](https://catalog.ldc.upenn.edu/LDC2001S97) ([part 2](https://github.com/BUTSpeechFIT/CALLHOME_sublists/issues/1)) | 31.6 | 28.4 | 20.1 |
| [DIHARD 3](https://catalog.ldc.upenn.edu/LDC2022S14) ([full](https://arxiv.org/abs/2012.01477)) | 26.9 | 21.4 | 17.2 |
| [Earnings21](https://github.com/revdotcom/speech-datasets) | 17.0 | 9.4 | 9.0 |
| [Ego4D](https://arxiv.org/abs/2110.07058) (dev.) | 61.5 | 51.2 | 45.8 |
| [MSDWild](https://github.com/X-LANCE/MSDWILD) | 32.8 | 25.4 | 19.7 |
| [RAMC](https://www.openslr.org/123/) | 22.5 | 22.2 | 11.1 |
| [REPERE](https://www.islrn.org/resources/360-758-359-485-0/) (phase2) | 8.2 | 7.9 | 7.6 |
| [VoxConverse](https://github.com/joonson/voxconverse) (v0.3) | 11.2 | 11.2 | 9.9 |
[Diarization error rate](http://pyannote.github.io/pyannote-metrics/reference.html#diarization) (in %)
- :hugs: pretrained [pipelines](https://hf.co/models?other=pyannote-audio-pipeline) (and [models](https://hf.co/models?other=pyannote-audio-model)) on [:hugs: model hub](https://huggingface.co/pyannote)
- :exploding_head: state-of-the-art performance (see [Benchmark](#benchmark))
- :snake: Python-first API
- :zap: multi-GPU training with [pytorch-lightning](https://pytorchlightning.ai/)
## Documentation
@@ -78,29 +130,6 @@ for turn, _, speaker in diarization.itertracks(yield_label=True):
- 2024-04-05 > [Offline speaker diarization (speaker-diarization-3.1)](tutorials/community/offline_usage_speaker_diarization.ipynb) by [Simon Ottenhaus](https://github.com/simonottenhauskenbun)
- 2024-09-24 > [Evaluating `pyannote` pretrained speech separation pipelines](tutorials/community/eval_separation_pipeline.ipynb) by [Clément Pagés](https://github.com/)
## Benchmark
Out of the box, `pyannote.audio` speaker diarization [pipeline](https://hf.co/pyannote/speaker-diarization-3.1) v3.1 is expected to be much better (and faster) than v2.x.
Those numbers are diarization error rates (in %):
| Benchmark | [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) | [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) | [pyannoteAI](https://www.pyannote.ai) |
| --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------------------------------------ | ------------------------------------------------ |
| [AISHELL-4](https://arxiv.org/abs/2104.03603) | 14.1 | 12.2 | 11.9 |
| [AliMeeting](https://www.openslr.org/119/) (channel 1) | 27.4 | 24.4 | 22.5 |
| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (IHM) | 18.9 | 18.8 | 16.6 |
| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (SDM) | 27.1 | 22.4 | 20.9 |
| [AVA-AVD](https://arxiv.org/abs/2111.14448) | 66.3 | 50.0 | 39.8 |
| [CALLHOME](https://catalog.ldc.upenn.edu/LDC2001S97) ([part 2](https://github.com/BUTSpeechFIT/CALLHOME_sublists/issues/1)) | 31.6 | 28.4 | 22.2 |
| [DIHARD 3](https://catalog.ldc.upenn.edu/LDC2022S14) ([full](https://arxiv.org/abs/2012.01477)) | 26.9 | 21.7 | 17.2 |
| [Earnings21](https://github.com/revdotcom/speech-datasets) | 17.0 | 9.4 | 9.0 |
| [Ego4D](https://arxiv.org/abs/2110.07058) (dev.) | 61.5 | 51.2 | 43.8 |
| [MSDWild](https://github.com/X-LANCE/MSDWILD) | 32.8 | 25.3 | 19.8 |
| [RAMC](https://www.openslr.org/123/) | 22.5 | 22.2 | 18.4 |
| [REPERE](https://www.islrn.org/resources/360-758-359-485-0/) (phase2) | 8.2 | 7.8 | 7.6 |
| [VoxConverse](https://github.com/joonson/voxconverse) (v0.3) | 11.2 | 11.3 | 9.4 |
[Diarization error rate](http://pyannote.github.io/pyannote-metrics/reference.html#diarization) (in %)
## Citations
If you use `pyannote.audio` please use the following citations:
+1
View File
@@ -29,6 +29,7 @@ dependencies = [
"torchmetrics>=1.6.1",
"soundfile>=0.13.1",
"matplotlib>=3.10.0",
"pyannoteai.sdk>=0.1.0",
]
[project.scripts]
@@ -0,0 +1,25 @@
# The MIT License (MIT)
#
# Copyright (c) 2025- pyannoteAI
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
from .speaker_diarization import PremiumSpeakerDiarization
__all__ = ["PremiumSpeakerDiarization"]
@@ -0,0 +1,123 @@
# The MIT License (MIT)
#
# Copyright (c) 2025- pyannoteAI
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
from pathlib import Path
from typing import Optional
from pyannote.core import Annotation, Segment
from pyannoteai.sdk import Client
from pyannote.audio import Pipeline
class PremiumSpeakerDiarization(Pipeline):
"""Wrapper around official pyannoteAI API client
Parameters
----------
token : str, optional
pyannoteAI API key created from https://dashboard.pyannote.ai.
Defaults to using `PYANNOTEAI_API_TOKEN` environment variable.
Usage
-----
>>> from pyannote.audio.pipelines.premium import PremiumSpeakerDiarization
>>> pipeline = PremiumSpeakerDiarization(token="{PYANNOTEAI_API_KEY}")
>>> speaker_diarization = pipeline("/path/to/your/audio.wav")
"""
def __init__(self, token: Optional[str] = None, **kwargs):
super().__init__()
self._client = Client(token)
def _to_annotation(self, completed_job: dict) -> Annotation:
"""Deserialize job output into pyannote.core Annotation"""
output = completed_job["output"]["diarization"]
job_id = completed_job["jobId"]
annotation = Annotation(uri=job_id)
for t, turn in enumerate(output):
segment = Segment(start=turn["start"], end=turn["end"])
speaker = turn["speaker"]
annotation[segment, t] = speaker
return annotation
def __call__(
self,
file: Path,
num_speakers: Optional[int] = None,
min_speakers: Optional[int] = None,
max_speakers: Optional[int] = None,
) -> Annotation:
"""Speaker diarization using pyannoteAI web API
This method will upload `file`, initiate a diarization job,
retrieve its output, and deserialize the latter into a good
old pyannote.core.Annotation instance.
Parameters
----------
file : AudioFile
Processed file.
num_speakers : int, optional
Force number of speakers to diarize. If not provided, the
number of speakers will be determined automatically.
min_speakers : int, optional
Not supported yet. Minimum number of speakers. Has no effect when `num_speakers` is provided.
max_speakers : int, optional
Not supported yet. Maximum number of speakers. Has no effect when `num_speakers` is provided.
Returns
-------
speaker_diarization : Annotation
Speaker diarization result (when successful)
Raises
------
PyannoteAIFailedJob
If the job failed
PyannoteAICanceledJob
If the job was canceled
HTTPError
If something else went wrong
"""
# upload file to pyannoteAI cloud API
media_url: str = self._client.upload(file)
# initiate diarization job
job_id = self._client.diarize(
media_url,
num_speakers=num_speakers,
min_speakers=min_speakers,
max_speakers=max_speakers,
confidence=False,
)
# retrieve job output (once completed)
job_output = self._client.retrieve(job_id)
# deserialize the output into a good-old Annotation instance
return self._to_annotation(job_output)
+6 -1
View File
@@ -70,6 +70,11 @@ def download_from_hf_hub(
else:
model_id, revision = checkpoint, None
# if provided token does not start with 'hf_', it is likely a pyannoteAI API key
# and therefore should not be passed to Huggingface Hub.
if token and not token.startswith("hf_"):
token = None
try:
return (
model_id,
@@ -95,7 +100,7 @@ It might be because the repository is private or gated:
* visit https://hf.co/{model_id} to accept user conditions
* visit https://hf.co/settings/tokens to create an authentication token
* load the {asset_file.name.lower()} with the `token` argument:
>>> {asset_file.name}.from_pretrained('{model_id}', token=...)
>>> {asset_file.name}.from_pretrained('{model_id}', token='hf_....')
"""
)
raise
Generated
+33 -29
View File
@@ -1,4 +1,5 @@
version = 1
revision = 1
requires-python = ">=3.10"
resolution-markers = [
"python_full_version < '3.11'",
@@ -375,7 +376,7 @@ name = "click"
version = "8.1.8"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "colorama", marker = "platform_system == 'Windows'" },
{ name = "colorama", marker = "sys_platform == 'win32'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
wheels = [
@@ -876,7 +877,7 @@ name = "ipykernel"
version = "6.29.5"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "appnope", marker = "platform_system == 'Darwin'" },
{ name = "appnope", marker = "sys_platform == 'darwin'" },
{ name = "comm" },
{ name = "debugpy" },
{ name = "ipython" },
@@ -1511,7 +1512,6 @@ name = "nvidia-cublas-cu12"
version = "12.4.5.8"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/7f/7f/7fbae15a3982dc9595e49ce0f19332423b260045d0a6afe93cdbe2f1f624/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0f8aa1706812e00b9f19dfe0cdb3999b092ccb8ca168c0db5b8ea712456fd9b3", size = 363333771 },
{ url = "https://files.pythonhosted.org/packages/ae/71/1c91302526c45ab494c23f61c7a84aa568b8c1f9d196efa5993957faf906/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b", size = 363438805 },
]
@@ -1520,7 +1520,6 @@ name = "nvidia-cuda-cupti-cu12"
version = "12.4.127"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/93/b5/9fb3d00386d3361b03874246190dfec7b206fd74e6e287b26a8fcb359d95/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:79279b35cf6f91da114182a5ce1864997fd52294a87a16179ce275773799458a", size = 12354556 },
{ url = "https://files.pythonhosted.org/packages/67/42/f4f60238e8194a3106d06a058d494b18e006c10bb2b915655bd9f6ea4cb1/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb", size = 13813957 },
]
@@ -1529,7 +1528,6 @@ name = "nvidia-cuda-nvrtc-cu12"
version = "12.4.127"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/77/aa/083b01c427e963ad0b314040565ea396f914349914c298556484f799e61b/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0eedf14185e04b76aa05b1fea04133e59f465b6f960c0cbf4e37c3cb6b0ea198", size = 24133372 },
{ url = "https://files.pythonhosted.org/packages/2c/14/91ae57cd4db3f9ef7aa99f4019cfa8d54cb4caa7e00975df6467e9725a9f/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338", size = 24640306 },
]
@@ -1538,7 +1536,6 @@ name = "nvidia-cuda-runtime-cu12"
version = "12.4.127"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/a1/aa/b656d755f474e2084971e9a297def515938d56b466ab39624012070cb773/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:961fe0e2e716a2a1d967aab7caee97512f71767f852f67432d572e36cb3a11f3", size = 894177 },
{ url = "https://files.pythonhosted.org/packages/ea/27/1795d86fe88ef397885f2e580ac37628ed058a92ed2c39dc8eac3adf0619/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5", size = 883737 },
]
@@ -1561,7 +1558,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/7a/8a/0e728f749baca3fbeffad762738276e5df60851958be7783af121a7221e7/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5dad8008fc7f92f5ddfa2101430917ce2ffacd86824914c82e28990ad7f00399", size = 211422548 },
{ url = "https://files.pythonhosted.org/packages/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 },
]
@@ -1570,7 +1566,6 @@ name = "nvidia-curand-cu12"
version = "10.3.5.147"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/80/9c/a79180e4d70995fdf030c6946991d0171555c6edf95c265c6b2bf7011112/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1f173f09e3e3c76ab084aba0de819c49e56614feae5c12f69883f4ae9bb5fad9", size = 56314811 },
{ url = "https://files.pythonhosted.org/packages/8a/6d/44ad094874c6f1b9c654f8ed939590bdc408349f137f9b98a3a23ccec411/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b", size = 56305206 },
]
@@ -1584,7 +1579,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/46/6b/a5c33cf16af09166845345275c34ad2190944bcc6026797a39f8e0a282e0/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d338f155f174f90724bbde3758b7ac375a70ce8e706d70b018dd3375545fc84e", size = 127634111 },
{ url = "https://files.pythonhosted.org/packages/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 },
]
@@ -1596,7 +1590,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/96/a9/c0d2f83a53d40a4a41be14cea6a0bf9e668ffcf8b004bd65633f433050c0/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_aarch64.whl", hash = "sha256:9d32f62896231ebe0480efd8a7f702e143c98cfaa0e8a76df3386c1ba2b54df3", size = 207381987 },
{ url = "https://files.pythonhosted.org/packages/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 },
]
@@ -1605,7 +1598,6 @@ name = "nvidia-cusparselt-cu12"
version = "0.6.2"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/98/8e/675498726c605c9441cf46653bd29cb1b8666da1fb1469ffa25f67f20c58/nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:067a7f6d03ea0d4841c85f0c6f1991c5dda98211f6302cb83a4ab234ee95bef8", size = 149422781 },
{ url = "https://files.pythonhosted.org/packages/78/a8/bcbb63b53a4b1234feeafb65544ee55495e1bb37ec31b999b963cbccfd1d/nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:df2c24502fd76ebafe7457dbc4716b2fec071aabaed4fb7691a201cde03704d9", size = 150057751 },
]
@@ -1622,7 +1614,6 @@ name = "nvidia-nvjitlink-cu12"
version = "12.4.127"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/02/45/239d52c05074898a80a900f49b1615d81c07fceadd5ad6c4f86a987c0bc4/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83", size = 20552510 },
{ url = "https://files.pythonhosted.org/packages/ff/ff/847841bacfbefc97a00036e0fce5a0f086b640756dc38caea5e1bb002655/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57", size = 21066810 },
]
@@ -1631,7 +1622,6 @@ name = "nvidia-nvtx-cu12"
version = "12.4.127"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/06/39/471f581edbb7804b39e8063d92fc8305bdc7a80ae5c07dbe6ea5c50d14a5/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7959ad635db13edf4fc65c06a6e9f9e55fc2f92596db928d169c0bb031e88ef3", size = 100417 },
{ url = "https://files.pythonhosted.org/packages/87/20/199b8713428322a2f22b722c62b8cc278cc53dffa9705d744484b5035ee9/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a", size = 99144 },
]
@@ -2002,7 +1992,6 @@ wheels = [
[[package]]
name = "pyannote-audio"
version = "3.3.3.dev59+g45d30114"
source = { editable = "." }
dependencies = [
{ name = "asteroid-filterbanks" },
@@ -2014,6 +2003,7 @@ dependencies = [
{ name = "pyannote-database" },
{ name = "pyannote-metrics" },
{ name = "pyannote-pipeline" },
{ name = "pyannoteai-sdk" },
{ name = "pytorch-metric-learning" },
{ name = "rich" },
{ name = "safetensors" },
@@ -2064,6 +2054,7 @@ requires-dist = [
{ name = "pyannote-database", specifier = ">=6.0.0rc1" },
{ name = "pyannote-metrics", specifier = ">=4.0.0rc1" },
{ name = "pyannote-pipeline", specifier = ">=4.0.0rc2" },
{ name = "pyannoteai-sdk", specifier = ">=0.1.0" },
{ name = "pytest", marker = "extra == 'test'", specifier = ">=8.3.4" },
{ name = "pytorch-metric-learning", specifier = ">=2.8.1" },
{ name = "rich", specifier = ">=13.9.4" },
@@ -2079,6 +2070,7 @@ requires-dist = [
{ name = "transformers", marker = "extra == 'separation'", specifier = ">=4.48.3" },
{ name = "typer", marker = "extra == 'cli'", specifier = ">=0.15.1" },
]
provides-extras = ["cli", "dev", "doc", "separation", "test"]
[package.metadata.requires-dev]
dev = [{ name = "ipykernel", specifier = ">=6.29.5" }]
@@ -2145,6 +2137,18 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/8c/c8/86d75670b7deab167989fca5dbb050648dd0349c6a9ddd5e97d0bc07286f/pyannote_pipeline-4.0.0rc2-py3-none-any.whl", hash = "sha256:2307b5ba2c2233f61e998a324db06e62f1c4c2517df28140cff591a894ab0c93", size = 22254 },
]
[[package]]
name = "pyannoteai-sdk"
version = "0.1.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "requests" },
]
sdist = { url = "https://files.pythonhosted.org/packages/2f/14/c9fcef3f76cb4137234bb058ca8079951325d815c2c3af56a8c30be57a11/pyannoteai_sdk-0.1.0.tar.gz", hash = "sha256:a43457574b128f570a4899d27995099b3e34185bf380a4c20cdc3e26ad623907", size = 13675 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/11/19/ac42327801ec858a03ff4d935782b1b7a9dc808f844b2c027354954a218c/pyannoteai_sdk-0.1.0-py3-none-any.whl", hash = "sha256:26cb6541f448baad351d69f81a36abac75b8366e4fe9d6eeade47c70f4bc459a", size = 8029 },
]
[[package]]
name = "pycparser"
version = "2.22"
@@ -3197,22 +3201,22 @@ dependencies = [
{ name = "fsspec" },
{ name = "jinja2" },
{ name = "networkx" },
{ name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cusparselt-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-cusparselt-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "setuptools", marker = "python_full_version >= '3.12'" },
{ name = "sympy" },
{ name = "triton", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
{ name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
{ name = "typing-extensions" },
]
wheels = [
@@ -3356,7 +3360,7 @@ name = "tqdm"
version = "4.67.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "colorama", marker = "platform_system == 'Windows'" },
{ name = "colorama", marker = "sys_platform == 'win32'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a8/4b/29b4ef32e036bb34e4ab51796dd745cdba7ed47ad142a9f4a1eb8e0c744d/tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2", size = 169737 }
wheels = [