Hugging Face's logo

fractalego
/
personal-speech-to-text-model

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
1
Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Personal speech to text model

s2t models often do not understand my accent, so I fine tuned this one from "facebook/wav2vec2-large-robust-ft-swbd-300h" using about 1000 recordings of my voice.

Do not download unless you have exactly my accent.

Downloads last month
2,296
Inference API
Automatic Speech Recognition
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using fractalego/personal-speech-to-text-model 1