FunASR

Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.

OpenAI Whisper ASR Webservice API

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.