awslabs/speech-representations
Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)
This project helps speech scientists and researchers create detailed numerical representations from raw audio. You provide speech recordings (WAV files), and it outputs specialized feature vectors that capture acoustic information. These outputs are crucial for training and evaluating advanced speech recognition, speaker identification, and language detection systems.
104 stars. No commits in the last 6 months.
Use this if you need to extract high-quality, contextualized acoustic features from speech audio for use in machine learning models.
Not ideal if you are looking for a fully maintained toolkit for training and fine-tuning these models, as this repository is not actively updated.
Stars
104
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/awslabs/speech-representations"
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