jreremy/conformer
Pytorch implementation of conformer with with training script for end-to-end speech recognition on the LibriSpeech dataset.
This project helps developers build and train speech recognition models from scratch. It takes audio datasets (like LibriSpeech) as input and outputs a trained model that can convert spoken language into text. It's designed for machine learning engineers and researchers focused on developing advanced audio processing and speech-to-text systems.
No commits in the last 6 months.
Use this if you are a machine learning developer or researcher looking to implement, train, or experiment with a Conformer model for end-to-end speech recognition.
Not ideal if you are an end-user seeking a pre-built speech-to-text application or an off-the-shelf solution for transcribing audio.
Stars
28
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
May 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jreremy/conformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment