Models
MOSS-Transcribe-Diarize
OpenMOSS/MOSS-Transcribe-Diarize
An 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.
Topics
Related projects
MOSS-TTS4.3kAn open-source speech model family for long-form TTS, dialogue synthesis, voice design, and streaming speech.
Fun-ASR1.6kTongyi Lab's open LLM-based speech recognition family covering Chinese dialects and 31 languages, with FunASR, vLLM, and on-device runtimes.
SALMONN1.6kByteDance's family of multimodal large language models for speech, audio and audio-visual understanding, released with model checkpoints and inference and training code.
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.
FunASR21kAn industrial speech recognition toolkit covering training, inference, streaming ASR, VAD, punctuation, speaker diarization and OpenAI-compatible serving.
speechbrain11.9kA PyTorch speech toolkit with recipes and pretrained models for recognition, enhancement, separation, and spoken language tasks.