gooofy/zamia-speech
Open tools and data for cloudless automatic speech recognition
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.
Stars
446
Forks
84
Language
Python
License
LGPL-3.0
Category
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.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
istupakov/onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition
haoheliu/voicefixer
General Speech Restoration