Update config.json
#1
by
arsen7076
- opened
No description provided.
Solve error for run
Thank you!
At this point, we already have new uploaded models (like zoo) in our org profile, that are 100% compatible with transformers and Inference API 🤗
Ar4ikov
changed pull request status to
merged
But that seems to be not working, because you should use that in your self-provided code with trust_remote_code=True
arguments when pulling weights.
TRUST = True
config = AutoConfig.from_pretrained('Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition', trust_remote_code=TRUST)
model_ = AutoModel.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=TRUST)
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_.to(device)
I leave this merge here at master cause no effect.