Audio-to-Audio
Transformers
Moshi
full-duplex
speech-to-speech
spoken-dialogue
tokenizer
multilingual
personaplex
qwen3
Instructions to use RetentionLabs/PolyPlex-11B-CJKE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RetentionLabs/PolyPlex-11B-CJKE with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RetentionLabs/PolyPlex-11B-CJKE", device_map="auto") - Moshi
How to use RetentionLabs/PolyPlex-11B-CJKE with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "RetentionLabs/PolyPlex-11B-CJKE" # 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("RetentionLabs/PolyPlex-11B-CJKE") # 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
Download processor_config.json from RetentionLabs/PolyPlex-11B-CJKE: direct link, hf CLI and curl.
- Browser
- Download file 751 Bytes
-
https://huggingface.co/RetentionLabs/PolyPlex-11B-CJKE/resolve/main/processor_config.json
- Command line
-
hf download hf://RetentionLabs/PolyPlex-11B-CJKE/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/RetentionLabs/PolyPlex-11B-CJKE/resolve/main/processor_config.json
751 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_polyplex.PolyplexProcessor" | |
| }, | |
| "codec_name_or_path": "kyutai/mimi", | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_polyplex.PolyplexProcessor" | |
| }, | |
| "chunk_length_s": null, | |
| "feature_extractor_type": "EncodecFeatureExtractor", | |
| "feature_size": 1, | |
| "overlap": null, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000 | |
| }, | |
| "num_codebooks": 8, | |
| "processor_class": "PolyplexProcessor", | |
| "silence_codes": [ | |
| 948, | |
| 243, | |
| 1178, | |
| 546, | |
| 1736, | |
| 1030, | |
| 1978, | |
| 2008 | |
| ], | |
| "sine_codes": [ | |
| 430, | |
| 1268, | |
| 381, | |
| 1611, | |
| 1095, | |
| 1495, | |
| 56, | |
| 472 | |
| ] | |
| } | |