biyoml/PyTorch-End-to-End-ASR-on-TIMIT
Attention-based end-to-end ASR on TIMIT in PyTorch
This project helps researchers and students working on speech recognition by providing a robust system for converting spoken audio into phoneme sequences. You feed it audio recordings from the TIMIT dataset, and it outputs the phonetic transcription of the speech. This is ideal for those studying or experimenting with end-to-end automatic speech recognition (ASR) models.
No commits in the last 6 months.
Use this if you need a working, attention-based model to transcribe speech phonetically from the TIMIT dataset and want to reproduce or build upon established ASR research.
Not ideal if you need to transcribe speech into text (words, not phonemes) or work with a different speech dataset outside of TIMIT.
Stars
18
Forks
6
Language
Python
License
—
Category
Last pushed
Nov 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/biyoml/PyTorch-End-to-End-ASR-on-TIMIT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project