News for hackers. Stuff that matters.
Re:OpenAI Audio Models by nickthegreek on Thursday March 20, 2025 @01:40PM (#43426325)
Indeed. Right now I think our open choices are Piper, Kokoro and Orpheus.
Re:OpenAI Audio Models by DrPhish on Thursday March 20, 2025 @02:05PM (#43426734)
In my opinion GPT-SoVITS is the best if you can put in the effort. I'm still using v2 since the output is so good. Its also the best multilingual one in my testing on Japanese inputs.
Re:OpenAI Audio Models by nickthegreek on Thursday March 20, 2025 @04:03PM (#43428208)
hadnt messed with that one before. my needs are more real time for voice assistant but was neat to play with on hugginface.

https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2

Re:OpenAI Audio Models by pzo on Thursday March 20, 2025 @03:57PM (#43428134)
can it support more languages rather than only English, Chinese, Japanese, Korean?
Re:OpenAI Audio Models by GaggiX on Thursday March 20, 2025 @02:06PM (#43426744)
He was talking about STT models, not TTS. Whisper is open source and a good solution in many cases (in particular finetuned ones).
Re:OpenAI Audio Models by pzo on Thursday March 20, 2025 @03:50PM (#43428043)
regarding STT we got also today 2 new models from Nvidia:

https://huggingface.co/nvidia/canary-180m-flash

https://huggingface.co/nvidia/canary-1b-flash

second in Open ASR leaderboard https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

Sadly only supports 4 languages (english, german, spanish, french)