Audio-to-Audio
Moshi
English
speech-to-speech
full-duplex
spoken-dialogue
conversational-ai
voice-agent
voice-assistant
real-time
indian-english
indian-accent
india
customer-support
call-center
barge-in
mimi
lora
audio
Instructions to use IOTEverythin/roxi-duplex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use IOTEverythin/roxi-duplex with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "IOTEverythin/roxi-duplex" # 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("IOTEverythin/roxi-duplex") # 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) - Notebooks
- Google Colab
- Kaggle
| { | |
| "dim": 4096, | |
| "text_card": 32000, | |
| "existing_text_padding_id": 3, | |
| "n_q": 16, | |
| "dep_q": 8, | |
| "card": 2048, | |
| "num_heads": 32, | |
| "num_layers": 32, | |
| "hidden_scale": 4.125, | |
| "causal": true, | |
| "layer_scale": null, | |
| "context": 3000, | |
| "max_period": 10000, | |
| "gating": "silu", | |
| "norm": "rms_norm_f32", | |
| "positional_embedding": "rope", | |
| "depformer_dim": 1024, | |
| "depformer_dim_feedforward": 4224, | |
| "depformer_num_heads": 16, | |
| "depformer_num_layers": 6, | |
| "depformer_layer_scale": null, | |
| "depformer_multi_linear": true, | |
| "depformer_context": 8, | |
| "depformer_max_period": 10000, | |
| "depformer_gating": "silu", | |
| "depformer_pos_emb": "none", | |
| "depformer_weights_per_step": true, | |
| "delays": [ | |
| 0, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "lora": true, | |
| "lora_rank": 64, | |
| "lora_scaling": 2.0 | |
| } |