--- license: cc-by-nc-4.0 base_model: facebook/musicgen-medium pipeline_tag: text-to-audio tags: - music-generation - emotion-control - arxiv:2510.05875 --- # LARA-Gen Inference release for [LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment](https://arxiv.org/abs/2510.05875). `model.safetensors` and `av_encoder.safetensors` together contain the final-paper main checkpoint: experiment `59dc26ab`, epoch 30, embedded `best_state`. Both files are required. The included `laragen/` code implements the corresponding streaming Transformer and continuous VA conditioning. ## Install and generate Use Python 3.9 or 3.10, install FFmpeg with your system package manager, then run from this directory: ```bash python -m pip install -r requirements.txt python generate.py --arousal 7.4 --valence 5.8 --seed 204000 --output outputs/example.wav ``` Use matched PyTorch/torchaudio wheels for your platform. CUDA is recommended; `--device cpu` supports slow CPU inference. The WAV is 30 seconds, 32 kHz, mono, with loudness normalization. `--duration` accepts 0.5–30 seconds. A JSON sidecar records the inputs and seed. Attention uses native PyTorch SDPA with `backend='torch'` and `memory_efficient=true`. No xformers installation is required. Streaming generation retains its KV cache, including support for decoding multiple new tokens per call. Arousal and valence are continuous values in **[1, 9]**. Numeric conditioning uses `[arousal, valence]`, normalized by `(x-5)/4`. The original prompt spelling is preserved: `Genarate an instrumental music with arousal 7.40 and valence 5.80.` Sampling uses temperature 1, top-k 250, top-p 0 and CFG 3. Paper samples use seeds `204000 + sample index`. ```python from laragen import LaraGen model = LaraGen('.', device='cuda') audio = model.generate(arousal=7.4, valence=5.8, seed=204000) # [1, 1, 960000], before WAV loudness normalization ``` ## Frozen dependencies On first use the loader downloads the original frozen components from their public repositories: - T5-base: `t5-base`, revision `a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1`. - EnCodec: `facebook/encodec_32khz`, revision `d0c45384f6c44db055f78200cfdcb9c1c8706727`. For offline inference, download these snapshots on a connected machine: ```bash hf download t5-base --revision a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1 --include config.json model.safetensors spiece.model tokenizer.json tokenizer_config.json special_tokens_map.json --local-dir dependencies/t5-base hf download facebook/encodec_32khz --revision d0c45384f6c44db055f78200cfdcb9c1c8706727 --include config.json model.safetensors --local-dir dependencies/encodec export LARAGEN_T5_PATH="$PWD/dependencies/t5-base" export LARAGEN_CODEC_PATH="$PWD/dependencies/encodec" export HF_HUB_OFFLINE=1 export TRANSFORMERS_OFFLINE=1 ``` Then run `generate.py` as above. The loader uses FP32 modules with FP16 LM autocast on CUDA. Validated without xformers using PyTorch 2.1.1: CPU attention/streaming checks, CUDA FP16 streaming checks, and full 30-second generation on an NVIDIA A100 (32 kHz, mono, 960,000 samples). ## License Model weights: [CC BY-NC 4.0](LICENSE), inherited from [MusicGen](https://huggingface.co/facebook/musicgen-medium). Code: [MIT](LICENSE-CODE), with Meta/AudioCraft notices retained in adapted sources. External [T5](https://huggingface.co/google-t5/t5-base) and [EnCodec](https://huggingface.co/facebook/encodec_32khz) retain their own licenses.