Transformershuggingface/transformers
A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
PythonDeep learningLLMsNLP168.1k updated today
Speech and audio libraries
10 libraries, 9 updated this year
Speech recognition toolkits and on-device speech runtimes.
10 libraries
PythonDeep learningLLMsNLP
Kaldikaldi-asr/kaldi
Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.
C++15.5k updated 1y ago
Voskalphacep/vosk-api
An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.
C++Deep learning15.2k updated 9d ago
EspNetespnet/espnet
ESPnet is an end-to-end speech processing toolkit for tasks like speech recognition, translation, and enhancement, using PyTorch and Kaldi-style data processing.
PythonDeep learning10k updated today
wav2letterfacebookresearch/wav2letter
A simple and efficient end-to-end Automatic Speech Recognition (ASR) system from Facebook AI Research.
LuaGeneralDeep learning6.4k updated 1mo ago
CMU Sphinxcmusphinx/pocketsphinx
Open Source Toolkit For Speech Recognition purely based on Java speech recognition library.
Java4.4k updated 11d ago
tiny-audioalexkroman/tiny-audio
Minimal, hackable PyTorch/Hugging Face codebase for training LLM-based speech recognition by connecting a frozen pretrained speech encoder to a pretrained LLM through a small trained projector, with word timestamps, speaker diarization and a free course.
PythonLLMs175 updated 1d ago
VoxRTVoxRT/voxrt-asr-android
On-device streaming speech recognition SDK for Android with Kotlin bindings (JitPack). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
Kotlin20 updated 1mo ago
VoxRTVoxRT/voxrt-asr-ios
On-device streaming speech recognition SDK for iOS with Swift bindings (SPM). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
Swift15 updated 1mo ago
VoxRTVoxRT/voxrt-asr-linux
On-device streaming speech recognition runtime with C API for Linux (aarch64/x86_64). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
+19 updated 1mo ago