Aniemore

/

wav2vec2-xlsr-53-russian-emotion-recognition

like 10

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 🤗

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.