This model is a fine-tuned wav2vec2-BERT checkpoint for Cantonese automatic speech recognition. It was trained on the Common Voice dataset and other Cantonese speech corpora. The model is available on the Hugging Face Hub and supports inference through the Transformers pipeline for automatic-speech-recognition.
Wav2vec2 BERT Cantonese is a Speech to text project. It focuses on transcribing Cantonese speech into text with high accuracy. It is built as an open-source project for developers. Wav2vec2 BERT Cantonese is open source under the Open Source license. Wav2vec2 BERT Cantonese is available on the web and API.
It is developed by alvanlii.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do