Automatic Speech Recognition with Next-gen Kaldi

Language
Select a model
Decoding method
1 100
Whether to add punctuation (Only for Chinese)

This space shows how to do automatic speech recognition with Next-gen Kaldi.

Please visit https://k2-fsa.github.io/sherpa/ncnn/wasm/hf-spaces.html for streaming speech recognition with Next-gen Kaldi using WebAssembly.

It is running on CPU within a docker container provided by Hugging Face.

Please input audio files less than 30 seconds in this space.

Please see https://huggingface.co/spaces/k2-fsa/generate-subtitles-for-videos if you want to try files longer than 30 seconds.

For text to speech, please see https://huggingface.co/spaces/k2-fsa/text-to-speech

See more information by visiting the following links:

If you want to deploy it locally, please see https://k2-fsa.github.io/sherpa/