---
pipeline_tag: text-to-speech
library_name: transformers
base_model: CohereLabs/tiny-aya-fire
base_model_relation: finetune
license: cc-by-nc-4.0
language:
  - hi
  - bn
  - ta
  - te
  - mr
  - gu
  - kn
  - ml
  - pa
  - or
  - as
  - ur
  - ne
  - sa
  - mai
  - mni
  - brx
  - doi
  - kok
  - sat
  - ks
  - en
tags:
  - tts
  - text-to-speech
  - indic
  - multilingual
  - mimi
  - speech
---

<p align="center">
  <img src="assets/rumik-logo.png" alt="rumik.ai" width="100%">
</p>

<p align="center">
  <a href="https://rumik.ai/research/rumik-oss">blog</a> &nbsp; | &nbsp;
  <a href="https://huggingface.co/rumik-ai/rumik-oss-1">post-trained model</a> &nbsp; | &nbsp;
  <a href="https://x.com/rumik_ai">x</a> &nbsp; | &nbsp;
  <a href="https://discord.gg/wa7sWvq8ty">discord</a> &nbsp; | &nbsp;
  technical report: coming soon
</p>

# rumik-oss 1 base

rumik-oss 1 base is a **3b multilingual text-to-speech model** from rumik ai, released at the end of named-speaker training, before the subsequent delivery-control fine-tuning and reinforcement learning used for [rumik-oss 1](https://huggingface.co/rumik-ai/rumik-oss-1). it supports speaker-conditioned synthesis with **24 khz audio output** and provides a starting point for further speech-model training and adaptation.

## model overview

our [blog](https://rumik.ai/research/rumik-oss) describes the training curriculum and development of rumik-oss 1.

the model extends tiny aya fire with discrete audio tokens from the mimi codec. following the flattened codec-token formulation used in [llama-mimi](https://arxiv.org/abs/2509.14882), a single causal transformer predicts eight codebook tokens per audio frame before advancing to the next frame. the frozen mimi decoder reconstructs the generated sequence as a waveform.

training progresses from english speech generation to indic-language continuation and named-speaker adaptation. the released checkpoint includes **ira, aisha, siya, and zoya** and accepts native-script, romanized, or code-switched text. speaker conditioning uses a name prefix followed by the text to synthesize.

this base release has not undergone description-conditioned delivery or inline vocalization training. use the [post-trained model](https://huggingface.co/rumik-ai/rumik-oss-1) for tone, accent, pace, and vocalization controls.

## inference

rumik-oss 1 base generates **audio tokens**. decoding them to a waveform is a
separate step that uses the [mimi](https://huggingface.co/kyutai/mimi) codec,
bundled in this repository under `codec/`.

`transformers.pipeline("text-to-speech")` is not supported for this model.
use the [one-shot example](#one-shot-example) to generate audio tokens with
`generate_audio()` and decode them into a waveform with mimi.

### installation

```bash
pip install -r requirements.txt
```

requires an nvidia gpu with cuda support. the one-shot example below also
needs `soundfile` to write a wav.

### one-shot example

text in, `speech.wav` out:

```python
"""rumik-oss 1 base: text -> speech.wav"""
import soundfile as sf
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, MimiModel

REPO = "rumik-ai/rumik-oss-1-base"
SPEAKER = "Ira"
TEXT = "Hello, how are you today?"

tokenizer = AutoTokenizer.from_pretrained(REPO, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    REPO, trust_remote_code=True, dtype=torch.bfloat16
).eval().cuda()
mimi = MimiModel.from_pretrained(REPO, subfolder="codec").eval().cuda()

# [BOS] <text> Ira: text <audio>
# the tokenizer adds [BOS] itself, so it is not written here
prompt = f'<text>{SPEAKER}: {TEXT}<audio>'
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

# 1. text -> audio tokens
ids = model.generate_audio(**inputs, max_new_tokens=2048,
                           temperature=0.8, top_k=30, do_sample=True)
audio_tokens = ids[0].tolist()[inputs.input_ids.shape[1]:]

# 2. audio tokens -> codec frames -> waveform
codes = model.audio_tokens_to_codes(audio_tokens)
with torch.inference_mode():
    wav = mimi.decode(codes.to(mimi.device)).audio_values[0, 0]

sf.write("speech.wav", wav.float().cpu().numpy(), 24000)
print(f"{len(audio_tokens)} tokens -> {len(audio_tokens) / 100:.2f}s -> speech.wav")
```

`SPEAKER` accepts `Ira`, `Aisha`, `Siya`, or `Zoya`. the model was trained on
a flat token layout, not a chat template:

```text
[BOS] <text> {speaker}: spoken text <audio> ... </audio>
```

this checkpoint has no description-conditioned delivery or inline
vocalization controls; use the
[post-trained model](https://huggingface.co/rumik-ai/rumik-oss-1) for those.

### command line

```bash
python inference.py --speaker Ira --text "Hello, how are you today?" --output speech.wav
```

## further training

the release includes the language-model weights, learned stop predictor, tokenizer, and mimi codec. the model can be loaded through `AutoModelForCausalLM.from_pretrained(..., trust_remote_code=True)` for adaptation. preserve the bundled tokenizer's audio-token mapping when preparing training data. optimizer state is not included; further training starts with a new optimizer.

## license

rumik-oss 1 base is available for **research and non-commercial use** under [tiny aya fire's cc-by-nc 4.0 license with an acceptable-use addendum](https://cohere.com/cohere-labs-cc-by-nc-license).

permitted non-commercial uses include speech-synthesis research, benchmarking, teaching, and fine-tuning for research experiments. redistribution and adaptations must retain attribution, license links, upstream notices, and an indication of modifications. all use must comply with [cohere labs' acceptable-use policy](https://docs.cohere.com/docs/cohere-labs-acceptable-use-policy). the license does not grant permission for commercial products or paid synthesis services.

the bundled [mimi codec](https://huggingface.co/kyutai/mimi) is separately licensed under [cc-by-4.0](https://creativecommons.org/licenses/by/4.0/). its commercial permissions do not extend to the tiny aya-derived tts weights.

the full license text is in [`LICENSE`](LICENSE), and [`NOTICE.md`](NOTICE.md)
records the modifications made to tiny aya fire, as cc-by-nc 4.0 requires.

## acknowledgments

rumik-oss 1 base builds on [tiny aya fire](https://huggingface.co/CohereLabs/tiny-aya-fire), [mimi](https://huggingface.co/kyutai/mimi), [llama-mimi](https://arxiv.org/abs/2509.14882), and [torchtitan](https://github.com/pytorch/torchtitan). we thank their authors for making this work available.

## contact

[research@rumik.ai](mailto:research@rumik.ai)

## citation

if you find rumik-oss 1 base useful in your research, please cite our work:

```bibtex
@unpublished{govindu2026rumikoss1,
  title  = {{rumik-oss 1 technical report}},
  author = {Govindu Pranav and Anant Shukla and Suryansh Shakya and Aman Anand and Vatsal Bharti},
  year   = {2026},
  note   = {In preparation}
}
```