GitHub - fishaudio/fish-speech: Brand new TTS solutionYou signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert
`large-v3` release · openai/whisper · Discussion #1762
We're pleased to announce the latest iteration of Whisper, called large-v3. Whisper-v3 has the same architecture as the previous large models except the following minor differences: The input uses 128 Mel frequency bins instead of 80 A new language token for Cantonese The large-v3 model is trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GitHub - 2noise/ChatTTS: A generative speech model for daily dialogue.
Seed-TTS
GitHub - fishaudio/Bert-VITS2: vits2 backbone with multilingual-bert
GitHub - RVC-Boss/GPT-SoVITS: 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)