noahchalifour/rnnt-speech-recognition
End-to-end speech recognition using RNN Transducers in Tensorflow 2.0
This project helps developers build custom speech recognition systems that can convert spoken audio into written text. You provide audio files (like MP3s or WAVs) and corresponding text transcripts, and it produces a trained model capable of transcribing new audio. This tool is for machine learning engineers or AI researchers who need to develop or fine-tune their own speech-to-text engines.
249 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer looking to implement or experiment with a custom RNN-Transducer based speech recognition model from scratch.
Not ideal if you need an out-of-the-box speech-to-text solution without extensive programming or model training.
Stars
249
Forks
79
Language
Python
License
MIT
Category
Last pushed
Jul 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/noahchalifour/rnnt-speech-recognition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
pannous/tensorflow-speech-recognition
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks