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 Voice, TTS & speech product. It focuses on transcribing Cantonese speech into text with high accuracy. Wav2vec2 BERT Cantonese is an open-source project aimed at developers. The project is open source (Open Source). The product ships for the web and API.
It is developed by alvanlii, and the product first shipped in 2023.
Latest indexed changes and source events
alvanlii/wav2vec2-BERT-cantonese verified by the PulseGate indexer
