Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
As per the CLAP repo (https://github.com/LAION-AI/CLAP), clap was trained with 48KHz but audiocraft is using the audio samples at 44.1KHz to train with CLAP pre-trained weights. Is this correct or am I understanding it wrongly?
As per the CLAP repo (https://github.com/LAION-AI/CLAP), clap was trained with 48KHz but audiocraft is using the audio samples at 44.1KHz to train with CLAP pre-trained weights. Is this correct or am I understanding it wrongly?![image](https://github.com/facebookresearch/audiocraft/assets/8533649/d33c2789-1353-4748-80f0-4e5c373d3e17)