Libraries & frameworks
faster-whisper
SYSTRAN/faster-whisper
A fast Whisper transcription library built on CTranslate2, with quantization, batching, VAD filtering, and word timestamps.
Topics
Related projects
whisper.cpp55.1kA dependency-free, high-performance C/C++ port of Whisper for on-device speech recognition, with quantization, broad hardware acceleration, and many language bindings.
vosk-api15.2kAn offline speech recognition toolkit with small models and bindings for many languages, built for apps and devices.
speech-to-text-benchmark699A minimalist, extensible Python framework for benchmarking speech-to-text engines, comparing accuracy, latency, memory and compute across local and cloud providers on standard datasets.
nano-vllm16.3kA lightweight vLLM reimplementation in about 1,200 lines of Python delivering fast, readable offline LLM inference.
whisper-ctranslate21.4kA faster, OpenAI-compatible Whisper CLI client built on CTranslate2, adding speaker diarization, VAD filtering, live microphone transcription, and Docker images.
willow-inference-server511Willow Inference Server is a self-hosted, CUDA-optimized inference server exposing Whisper speech recognition, text-to-speech and LLM inference over REST, WebRTC and WebSocket APIs.