Models
Fun-ASR
QwenAudio/Fun-ASR
Tongyi Lab's open LLM-based speech recognition family covering Chinese dialects and 31 languages, with FunASR, vLLM, and on-device runtimes.
Topics
Related projects
FunASR21kAn industrial speech recognition toolkit covering training, inference, streaming ASR, VAD, punctuation, speaker diarization and OpenAI-compatible serving.
MOSS-Transcribe-Diarize2.3kAn open 0.9B end-to-end audio model for long-form transcription in 50+ languages, with speaker diarization, timestamps, and acoustic event awareness. The repo ships inference code, serving recipes, a subtitle web app, and fine-tuning guidance.
CrisperWhisper1.5kA multilingual speech recognition model for verbatim and intended transcription with precise word-level timestamps, distributed as model weights plus a Python inference package.
vosk-api15.2kAn offline speech recognition toolkit with small models and bindings for many languages, built for apps and devices.
espnet10kAn end-to-end speech processing toolkit on PyTorch covering recognition, synthesis, translation and enhancement with reproducible recipes.
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.