mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
Co-authored-by: Herve Bredin <hbredin@users.noreply.github.com>
104 KiB
104 KiB
In [1]:
!pip install -qqq pyannote.audio==3.1.1[2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m208.7/208.7 kB[0m [31m4.7 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m44.6/44.6 kB[0m [31m6.4 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m2.0/2.0 MB[0m [31m15.1 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m79.5/79.5 kB[0m [31m10.4 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m58.5/58.5 kB[0m [31m8.5 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m48.1/48.1 kB[0m [31m7.1 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m51.4/51.4 kB[0m [31m6.9 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m118.6/118.6 kB[0m [31m16.3 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m630.6/630.6 kB[0m [31m21.4 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m101.7/101.7 kB[0m [31m14.0 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m47.9/47.9 kB[0m [31m7.2 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m806.1/806.1 kB[0m [31m25.3 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m777.7/777.7 kB[0m [31m29.7 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m117.0/117.0 kB[0m [31m18.7 MB/s[0m eta [36m0:00:00[0m [?25h Preparing metadata (setup.py) ... [?25l[?25hdone Preparing metadata (setup.py) ... [?25l[?25hdone [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m413.4/413.4 kB[0m [31m29.9 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m1.3/1.3 MB[0m [31m39.8 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m59.6/59.6 kB[0m [31m9.3 MB/s[0m eta [36m0:00:00[0m [?25h Preparing metadata (setup.py) ... [?25l[?25hdone [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m233.4/233.4 kB[0m [31m27.2 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m116.4/116.4 kB[0m [31m14.5 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m78.6/78.6 kB[0m [31m12.0 MB/s[0m eta [36m0:00:00[0m [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m526.7/526.7 kB[0m [31m45.2 MB/s[0m eta [36m0:00:00[0m [?25h Building wheel for antlr4-python3-runtime (setup.py) ... [?25l[?25hdone Building wheel for docopt (setup.py) ... [?25l[?25hdone Building wheel for julius (setup.py) ... [?25l[?25hdone
In [3]:
# access your HF token
from google.colab import userdata
hf_token = userdata.get('HF_TOKEN')
# load the pretrained pipeline
from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained(
"pyannote/speaker-diarization-3.1",
use_auth_token=hf_token)config.yaml: 0%| | 0.00/469 [00:00<?, ?B/s]
/usr/local/lib/python3.10/dist-packages/pyannote/audio/pipelines/speaker_verification.py:43: UserWarning: torchaudio._backend.get_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. backend = torchaudio.get_audio_backend() /usr/local/lib/python3.10/dist-packages/pyannote/audio/pipelines/speaker_verification.py:53: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend(backend) /usr/local/lib/python3.10/dist-packages/pyannote/audio/tasks/segmentation/mixins.py:37: UserWarning: `torchaudio.backend.common.AudioMetaData` has been moved to `torchaudio.AudioMetaData`. Please update the import path. from torchaudio.backend.common import AudioMetaData
pytorch_model.bin: 0%| | 0.00/5.91M [00:00<?, ?B/s]
config.yaml: 0%| | 0.00/399 [00:00<?, ?B/s]
pytorch_model.bin: 0%| | 0.00/26.6M [00:00<?, ?B/s]
config.yaml: 0%| | 0.00/221 [00:00<?, ?B/s]
In [4]:
import torch
if torch.cuda.is_available():
gpu = torch.device("cuda")
pipeline.to(gpu)
else:
print("Please switch to (free) T4 GPU runtime.")In [5]:
!wget https://github.com/pyannote/pyannote-audio/raw/develop/tutorials/assets/sample.wav--2024-01-08 15:31:41-- https://github.com/pyannote/pyannote-audio/raw/develop/tutorials/assets/sample.wav Resolving github.com (github.com)... 140.82.113.4 Connecting to github.com (github.com)|140.82.113.4|:443... connected. HTTP request sent, awaiting response... 302 Found Location: https://raw.githubusercontent.com/pyannote/pyannote-audio/develop/tutorials/assets/sample.wav [following] --2024-01-08 15:31:41-- https://raw.githubusercontent.com/pyannote/pyannote-audio/develop/tutorials/assets/sample.wav Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ... Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 960104 (938K) [audio/wav] Saving to: ‘sample.wav’ sample.wav 100%[===================>] 937.60K --.-KB/s in 0.04s 2024-01-08 15:31:42 (25.7 MB/s) - ‘sample.wav’ saved [960104/960104]
In [6]:
diarization = pipeline("sample.wav")/usr/local/lib/python3.10/dist-packages/pyannote/audio/utils/reproducibility.py:74: ReproducibilityWarning: TensorFloat-32 (TF32) has been disabled as it might lead to reproducibility issues and lower accuracy. It can be re-enabled by calling >>> import torch >>> torch.backends.cuda.matmul.allow_tf32 = True >>> torch.backends.cudnn.allow_tf32 = True See https://github.com/pyannote/pyannote-audio/issues/1370 for more details. warnings.warn(
In [7]:
diarizationOut [7]:
In [8]:
from pyannote.audio import Model
model = Model.from_pretrained(
"pyannote/speaker-diarization-3.1",
use_auth_token=hf_token)[0;31m---------------------------------------------------------------------------[0m
[0;31mHTTPError[0m Traceback (most recent call last)
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_errors.py[0m in [0;36mhf_raise_for_status[0;34m(response, endpoint_name)[0m
[1;32m 285[0m [0;32mtry[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m--> 286[0;31m [0mresponse[0m[0;34m.[0m[0mraise_for_status[0m[0;34m([0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 287[0m [0;32mexcept[0m [0mHTTPError[0m [0;32mas[0m [0me[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/requests/models.py[0m in [0;36mraise_for_status[0;34m(self)[0m
[1;32m 1020[0m [0;32mif[0m [0mhttp_error_msg[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m-> 1021[0;31m [0;32mraise[0m [0mHTTPError[0m[0;34m([0m[0mhttp_error_msg[0m[0;34m,[0m [0mresponse[0m[0;34m=[0m[0mself[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 1022[0m [0;34m[0m[0m
[0;31mHTTPError[0m: 404 Client Error: Not Found for url: https://huggingface.co/pyannote/speaker-diarization-3.1/resolve/main/pytorch_model.bin
The above exception was the direct cause of the following exception:
[0;31mEntryNotFoundError[0m Traceback (most recent call last)
[0;32m<ipython-input-8-326f921b8812>[0m in [0;36m<cell line: 2>[0;34m()[0m
[1;32m 1[0m [0;32mfrom[0m [0mpyannote[0m[0;34m.[0m[0maudio[0m [0;32mimport[0m [0mModel[0m[0;34m[0m[0;34m[0m[0m
[0;32m----> 2[0;31m model = Model.from_pretrained(
[0m[1;32m 3[0m [0;34m"pyannote/speaker-diarization-3.1"[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[1;32m 4[0m use_auth_token=hf_token)
[0;32m/usr/local/lib/python3.10/dist-packages/pyannote/audio/core/model.py[0m in [0;36mfrom_pretrained[0;34m(cls, checkpoint, map_location, hparams_file, strict, use_auth_token, cache_dir, **kwargs)[0m
[1;32m 622[0m [0;34m[0m[0m
[1;32m 623[0m [0;32mtry[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m--> 624[0;31m path_for_pl = hf_hub_download(
[0m[1;32m 625[0m [0mmodel_id[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[1;32m 626[0m [0mHF_PYTORCH_WEIGHTS_NAME[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py[0m in [0;36m_inner_fn[0;34m(*args, **kwargs)[0m
[1;32m 116[0m [0mkwargs[0m [0;34m=[0m [0msmoothly_deprecate_use_auth_token[0m[0;34m([0m[0mfn_name[0m[0;34m=[0m[0mfn[0m[0;34m.[0m[0m__name__[0m[0;34m,[0m [0mhas_token[0m[0;34m=[0m[0mhas_token[0m[0;34m,[0m [0mkwargs[0m[0;34m=[0m[0mkwargs[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[1;32m 117[0m [0;34m[0m[0m
[0;32m--> 118[0;31m [0;32mreturn[0m [0mfn[0m[0;34m([0m[0;34m*[0m[0margs[0m[0;34m,[0m [0;34m**[0m[0mkwargs[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 119[0m [0;34m[0m[0m
[1;32m 120[0m [0;32mreturn[0m [0m_inner_fn[0m [0;31m# type: ignore[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py[0m in [0;36mhf_hub_download[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, local_dir_use_symlinks, user_agent, force_download, force_filename, proxies, etag_timeout, resume_download, token, local_files_only, legacy_cache_layout, endpoint)[0m
[1;32m 1236[0m [0;32mtry[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[1;32m 1237[0m [0;32mtry[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m-> 1238[0;31m metadata = get_hf_file_metadata(
[0m[1;32m 1239[0m [0murl[0m[0;34m=[0m[0murl[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[1;32m 1240[0m [0mtoken[0m[0;34m=[0m[0mtoken[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py[0m in [0;36m_inner_fn[0;34m(*args, **kwargs)[0m
[1;32m 116[0m [0mkwargs[0m [0;34m=[0m [0msmoothly_deprecate_use_auth_token[0m[0;34m([0m[0mfn_name[0m[0;34m=[0m[0mfn[0m[0;34m.[0m[0m__name__[0m[0;34m,[0m [0mhas_token[0m[0;34m=[0m[0mhas_token[0m[0;34m,[0m [0mkwargs[0m[0;34m=[0m[0mkwargs[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[1;32m 117[0m [0;34m[0m[0m
[0;32m--> 118[0;31m [0;32mreturn[0m [0mfn[0m[0;34m([0m[0;34m*[0m[0margs[0m[0;34m,[0m [0;34m**[0m[0mkwargs[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 119[0m [0;34m[0m[0m
[1;32m 120[0m [0;32mreturn[0m [0m_inner_fn[0m [0;31m# type: ignore[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py[0m in [0;36mget_hf_file_metadata[0;34m(url, token, proxies, timeout, library_name, library_version, user_agent)[0m
[1;32m 1629[0m [0;34m[0m[0m
[1;32m 1630[0m [0;31m# Retrieve metadata[0m[0;34m[0m[0;34m[0m[0m
[0;32m-> 1631[0;31m r = _request_wrapper(
[0m[1;32m 1632[0m [0mmethod[0m[0;34m=[0m[0;34m"HEAD"[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[1;32m 1633[0m [0murl[0m[0;34m=[0m[0murl[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py[0m in [0;36m_request_wrapper[0;34m(method, url, follow_relative_redirects, **params)[0m
[1;32m 383[0m [0;31m# Recursively follow relative redirects[0m[0;34m[0m[0;34m[0m[0m
[1;32m 384[0m [0;32mif[0m [0mfollow_relative_redirects[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;32m--> 385[0;31m response = _request_wrapper(
[0m[1;32m 386[0m [0mmethod[0m[0;34m=[0m[0mmethod[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[1;32m 387[0m [0murl[0m[0;34m=[0m[0murl[0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py[0m in [0;36m_request_wrapper[0;34m(method, url, follow_relative_redirects, **params)[0m
[1;32m 407[0m [0;31m# Perform request and return if status_code is not in the retry list.[0m[0;34m[0m[0;34m[0m[0m
[1;32m 408[0m [0mresponse[0m [0;34m=[0m [0mget_session[0m[0;34m([0m[0;34m)[0m[0;34m.[0m[0mrequest[0m[0;34m([0m[0mmethod[0m[0;34m=[0m[0mmethod[0m[0;34m,[0m [0murl[0m[0;34m=[0m[0murl[0m[0;34m,[0m [0;34m**[0m[0mparams[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0;32m--> 409[0;31m [0mhf_raise_for_status[0m[0;34m([0m[0mresponse[0m[0;34m)[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 410[0m [0;32mreturn[0m [0mresponse[0m[0;34m[0m[0;34m[0m[0m
[1;32m 411[0m [0;34m[0m[0m
[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_errors.py[0m in [0;36mhf_raise_for_status[0;34m(response, endpoint_name)[0m
[1;32m 294[0m [0;32melif[0m [0merror_code[0m [0;34m==[0m [0;34m"EntryNotFound"[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[1;32m 295[0m [0mmessage[0m [0;34m=[0m [0;34mf"{response.status_code} Client Error."[0m [0;34m+[0m [0;34m"\n\n"[0m [0;34m+[0m [0;34mf"Entry Not Found for url: {response.url}."[0m[0;34m[0m[0;34m[0m[0m
[0;32m--> 296[0;31m [0;32mraise[0m [0mEntryNotFoundError[0m[0;34m([0m[0mmessage[0m[0;34m,[0m [0mresponse[0m[0;34m)[0m [0;32mfrom[0m [0me[0m[0;34m[0m[0;34m[0m[0m
[0m[1;32m 297[0m [0;34m[0m[0m
[1;32m 298[0m [0;32melif[0m [0merror_code[0m [0;34m==[0m [0;34m"GatedRepo"[0m[0;34m:[0m[0;34m[0m[0;34m[0m[0m
[0;31mEntryNotFoundError[0m: 404 Client Error. (Request ID: Root=1-659c1570-229842ad49cdd505022bd7b3;3b3426ec-0f8e-49a4-8783-f5740d92a8ed)
Entry Not Found for url: https://huggingface.co/pyannote/speaker-diarization-3.1/resolve/main/pytorch_model.bin.In [9]:
# this does not work because `pyannote/speaker-diarization-3.1` is a not a `Model`, it is a `Pipeline`.