gooofy/zamia-speech

Open tools and data for cloudless automatic speech recognition

48
/ 100
Emerging

Provides production-ready ASR models built from VoxForge corpora using Kaldi nnet3-chain and wav2letter++ architectures, alongside complementary KenLM language models and Sequitur G2P components. Includes Python training scripts for constructing custom models from speech and text corpora, with support for model adaptation and audiobook segmentation workflows. Integrates with py-kaldi-asr for inference and offers pre-trained English/German models optimized across resource tiers from embedded (TDNN_250) to high-accuracy (TDNN_f) configurations.

446 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

446

Forks

84

Language

Python

License

LGPL-3.0

Last pushed

Mar 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/gooofy/zamia-speech"

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