|
--- |
|
license: cc-by-nc-4.0 |
|
pipeline_tag: text-to-audio |
|
--- |
|
|
|
# MusicGen Static OpenVINO(TM) Models |
|
|
|
This repo stores MusicGen (and related) models, and other collateral that have been ported to OpenVINO IR format. |
|
|
|
These models are used to run *Music Generation* feature within this project: https://github.com/intel/openvino-plugins-ai-audacity |
|
|
|
## Description of collateral stores in *Files* |
|
* **musicgen_small_enc_dec_tok_openvino_models.zip**: This stores the following models that have been ported to OpenVINO IR format: |
|
* Tokenizer IR generated using [openvino tokenizers](https://github.com/openvinotoolkit/openvino_tokenizers) |
|
* facebook/encodec_32khz model, both encoder and decoder. |
|
* T5 text encoder |
|
|
|
* **musicgen_small_mono_openvino_models.zip**: This stores the [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) model that has been converted into [several] OpenVINO IR files. |
|
* **musicgen_small_stereo_openvino_models.zip**: This stores the [facebook/musicgen-stereo-small](https://huggingface.co/facebook/musicgen-stereo-small) model that has been converted into [several] OpenVINO IR files. |
|
|
|
**For more details about intended use of the model, datasets, limitations, etc., these details can be found in the Model Card within original model repo:** |
|
https://huggingface.co/facebook/musicgen-small |
|
https://huggingface.co/facebook/musicgen-stereo-small |
|
|