FireRedASR
FireRedASR copied to clipboard
FireRedTeam
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 recogn...
I do not see any reference related to using vad models for long audio files. Will you support this feature in the future? For instance, Whisper and SenseVoice both support...
numpy>2 seems not allowed. sentencepiece is not included in the requirements.txt, which could cause error when running speech2txt.py.
这边看到在README中python usage的解码参数，与inference_fireredasr_aed.sh中默认的解码参数有些不同，想了解一下默认的解码参数是哪一个，感谢！
Hi there! Thank you for perfect ASR models. Is any chance to get the manual to train on other language?
Metadata
Owner
Metadata
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 recogn...