freewym/espresso

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

46
/ 100
Emerging

Espresso helps researchers and developers build advanced automatic speech recognition (ASR) systems. It takes audio data and language model configurations as input and produces highly accurate text transcripts from spoken language. This toolkit is ideal for speech scientists and machine learning engineers developing new speech-to-text technologies.

940 stars. No commits in the last 6 months.

Use this if you are a researcher or developer who needs to train state-of-the-art, end-to-end neural speech recognition models on large datasets.

Not ideal if you are looking for an out-of-the-box speech-to-text application for immediate use, rather than a development toolkit.

speech-to-text voice-AI-development audio-processing natural-language-processing machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

940

Forks

116

Language

Python

License

Last pushed

Sep 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/freewym/espresso"

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