not able to pyannote/segmentation even though i can download it from browser

[erich23]

trying to run the most basic script with my access token

# 2. visit hf.co/settings/tokens to create an access token
# 3. instantiate pretrained speaker diarization pipeline
from pyannote.audio import Pipeline
from pyannote.audio import Model
import sys

token=<MY_ACCESS_TOKEN>
audio_file = sys.argv[0]

pipeline = Pipeline.from_pretrained("pyannote/[email protected]",
                                    use_auth_token=token)

# apply the pipeline to an audio file
diarization = pipeline(audio_file)

# dump the diarization output to disk using RTTM format
with open("audio.rttm", "w") as rttm:
    diarization.write_rttm(rttm)```

but i get this issue:

huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error: Repository Not Found for url: https://huggingface.co/pyannote/segmentation/resolve/2022.07/pytorch_model.bin. If the repo is private, make sure you are authenticated. (Request ID: P8aN1NNG9cBfvo82o6MO8)

thing is the repository isn't even private, i can download pytorch_model.bin directly from my browser

[mezaros]

Token requirement feels a little like a fiasco.

[Bagfish]

pipeline = Pipeline.from_pretrained("pyannote/[email protected]",
use_auth_token=token)

the code ' use_auth_token=token' didn't exist in pyannote-audio2.0 ,when it up to 2.1 it requires token.

[hbredin]

I have just updated the FAQ with instructions on how to use pretrained models and pipelines offline.