How to use efficient-nlp/stt-1b-en_fr-quantized with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "efficient-nlp/stt-1b-en_fr-quantized" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("efficient-nlp/stt-1b-en_fr-quantized") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes)
