kotoba-tech/kotoba-speech-v0.1
Text-to-Speech
•
Updated
•
12
•
17
Transcribe audio to text with timestamps
Generate images from Japanese prompts
Note date: 2024.04.22 X: https://x.com/SakanaAILabs/status/1782207884170080407 article: https://sakana.ai/evosdxl-jp/
Note date: 2024.04.22 X: https://twitter.com/tech_nichijo/status/1782176882609602847
Transcribe and translate Japanese & English audio
Evaluating LMMs on Japanese subjects
Browse and view questions from the JMMMU dataset
Generate Japanese speech from text
Whisper model to transcript japanese audio to katakana.
Transcribe audio to furigana text