A wav2vec2 XLS-R model fine-tuned for Nepali automatic speech recognition. Hosted on Hugging Face, it enables developers to build speech-to-text applications for the Nepali language using standard Transformers pipelines. The model was trained on OpenSLR data and supports local or cloud inference.
In the Voice, TTS & speech space, Wav2vec2 Xlsr Nepali takes a focused approach. It focuses on converting Nepali spoken audio into written text. Wav2vec2 Xlsr Nepali is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web and API.
It is developed by gagan3012, and the product first shipped in 2022. Among its 3 catalogued features are Automatic Speech Recognition, Transformers Compatible, and Model Card.
Latest indexed changes and source events
gagan3012/wav2vec2-xlsr-nepali verified by the PulseGate indexer
Other apps tracked under the same category.