LLMLingua
π
137
Compress prompts to reduce token usage
A unified multimodal understanding and generation model.
Clone a voice and generate speech from text
Generate synchronized audio for videos from text prompts
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Huggingface space for JanusFlow-1.3B
What happened in open-source AI this year, and whatβs next?
Transcribe audio files into text instantly