#Voice mode return "thanks for watching"
1 messages · Page 1 of 1 (latest)
@ancient wave
Please follow the posting guidelines.
For better assistance from the community or an OpenAI team member, please follow the posting guidelines by clicking the button below.
➜ Need to contact OpenAI support? Visit https://help.openai.com
It’s because whisper was trained on large amounts of YouTube data. And the model of whisper used for voice chat is very low quality compared to the model of whisper used for speech to text non voice mode (little microphone icon) no one other then OpenAI knows why they did this, seems really dumb but 🤷♂️