yh1008/speech-to-text

mixlingual speech recognition system; hybrid (GMM+NNet) model; Kaldi + Keras

36
/ 100
Emerging

This project helps people who mix English and Chinese in the same sentences when speaking, like many bilingual individuals. It takes audio recordings that contain both languages spoken together and accurately transcribes them into text. The output is a written record of the mixed-language speech, useful for anyone who needs to convert their bilingual conversations into text.

No commits in the last 6 months.

Use this if you need to accurately convert spoken audio containing both Chinese and English in the same sentences into a written transcript.

Not ideal if your audio is purely monolingual (only English or only Chinese) or if you require translation between languages rather than transcription of mixed speech.

bilingual-communication speech-to-text mixed-language-transcription audio-processing multilingual-messaging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

71

Forks

19

Language

Jupyter Notebook

License

Last pushed

Nov 20, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yh1008/speech-to-text"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.