Next-gen Kaldi: Generate subtitles for videos

Language

25 European languages 超多种中文方言 Chinese+English Chinese+English+Korean+Japanese+Cantoes(中英韩日粤语) Chinese English Russian Korean Thai Japanese

Select a model

Whether to add punctuation

Yes No

Upload from disk

Output

Generated subtitles

Recognized speech from uploaded video file (srt format)

Recognized speech from uploaded video file (all in one)

Upload audio from disk

Generated subtitles

Recognized speech from uploaded audio file (srt format)

Recognized speech from uploaded audio file (all in one)

URL

Audio

Generated subtitles

Recognized speech from audio URL (srt format)

Recognized speech from audio URL (all in one)

This space shows how to generate subtitles/captions with Next-gen Kaldi.

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

Please find test video files at https://huggingface.co/csukuangfj/vad/tree/main

See more information by visiting the following links:

https://github.com/k2-fsa/sherpa-onnx
https://github.com/k2-fsa/icefall
https://github.com/k2-fsa/k2
https://github.com/lhotse-speech/lhotse

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

·

Built with Gradio logo

·