adi-gov-tw/Taiwan-Tongues-ASR-CE

Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

BlueMagpie-TTS

ASRDeepspeech x Sakura-ML (English/Japanese) with deepspeech2 model in pytorch with support from Zakuro AI.

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

Traditional Mandarin LLMs for Taiwan