# Attribution and modifications

rumik-oss 1 base is a speech-adapted derivative of CohereLabs/tiny-aya-fire.
Rumik AI added audio-token embeddings and a learned stop predictor and trained
the model for multilingual, named-speaker speech synthesis.

- Tiny Aya Fire: https://huggingface.co/CohereLabs/tiny-aya-fire
- License: https://cohere.com/cohere-labs-cc-by-nc-license
- Acceptable-use policy: https://docs.cohere.com/docs/cohere-labs-acceptable-use-policy

CC-BY-NC 4.0 requires that redistribution indicate what was changed relative to
the upstream material. The modifications are:

1. Vocabulary extended from 261,008 to 277,395 tokens:
   - 16,384 Mimi codec unit tokens `<code>_<quantizer>`, ids 261008-277391
   - 3 structure delimiters `<text>`, `<audio>`, `</audio>`, ids 277392-277394

   Input and output embedding matrices were resized accordingly.

2. A stop-prediction head (`stop_predictor`) was added on top of the final
   hidden state to terminate audio generation.

3. The model was trained for multilingual, named-speaker text-to-speech,
   progressing from English through Indic-language continuation to
   named-speaker adaptation.

4. Model class and configuration are provided as `RumikOSSForCausalLM` /
   `RumikOSSConfig` (model_type `rumik_oss`), subclassing the transformers
   Cohere2 implementation. This is not a chat model and ships no chat
   template; it uses the flat prompt layout documented in README.md.

The delivery-control fine-tuning and reinforcement learning that follow this
checkpoint are applied in
[rumik-oss 1](https://huggingface.co/rumik-ai/rumik-oss-1).

## Bundled codec

The unmodified Mimi codec in `codec/` is by Kyutai, distributed under CC BY 4.0.

- Mimi: https://huggingface.co/kyutai/mimi
- License: https://creativecommons.org/licenses/by/4.0/

The codec's license does not replace the license governing the TTS model.