Nara Mini v1

Nara Mini v1 is a Kokoro-based text-to-speech model adapted for Burmese and English, with four preset voices and local inference support.

Nara Audio website

Attribution when redistributing: commercial use is permitted under Apache 2.0. If you redistribute this model or a derivative, preserve the applicable Nara Mini v1 attribution and supply the required license and notices. See Attribution and redistribution below.

The four voices were developed using synthetic speech generated with VoxCPM2. The exact starting Kokoro checkpoint version has not been recorded in the available release documentation.

Voices

Voice ID Display name
shoon Shoon
thazin Thazin
ko-banyar Ko Banyar
htet-myat Htet Myat

Each voice uses its own network and matching voicepack. Audio output is 24 kHz mono. Matching voice metadata supplies the vocabulary and style vectors.

Text processing

Inference uses Nara Mini v1's Burmese pronunciation rules, exceptions lexicon, English phonemization, and matching symbol IDs. Burmese number normalization converts supported numeric expressions to spoken words before phonemization.

Export formats

weights/<voice>/model.safetensors contains the original full-precision inference tensors. Keys have the form <module>.<parameter>, with modules bert, bert_encoder, predictor, text_encoder, and decoder. The matching architecture settings are in config.json. The vocabulary, style vectors, and length-bin centers are in onnx/<voice>/voice.json.

The mobile ONNX export in onnx/<voice>/ uses a full-precision encoder and a selectively quantized INT8 decoder, with matching voice.json metadata. packages/nara-mini-1-<voice>.nara packages the ONNX graphs and metadata with file checksums for installation in the Nara app. SHA256SUMS records release file hashes.

Run inference

Use Python 3.10 or newer.

pip install huggingface_hub
hf download YeeNyunn/nara-mini-v1 --local-dir nara-mini-v1
cd nara-mini-v1
pip install -r requirements.txt
python synthesize.py --voice shoon --text "α€™α€„α€Ία€Ήα€‚α€œα€¬α€•α€«α‹ Hello world." --output speech.wav

The example runs the ONNX encoder and decoder on CPU. Use --threads to set the CPU thread count. Use --no-normalize-numbers to preserve numeric text. English phonemization uses Misaki and its eSpeak dependency. Those dependencies retain their respective licenses.

Limitations

Pronunciation and prosody can vary with text and language mixing. Number normalization follows Burmese reading rules, including in mixed-language text. Long passages are processed in shorter pieces. Performance depends on device hardware, export format, and passage length.

License and acknowledgments

Nara Mini v1 is released under Apache 2.0. See LICENSE and NOTICE.

Kokoro provides the base model. VoxCPM2 provided synthetic speech used to develop the four preset voices.

Attribution and redistribution

Nara Mini v1 is available for commercial and non-commercial use under the Apache License 2.0. Redistribution of the model or derivative works must comply with that license, including section 4:

  • Give recipients a copy of the Apache 2.0 license.
  • For distributed derivative works, include a readable copy of the applicable attribution notices from NOTICE. These identify Nara Mini v1, Nara contributors, https://naraaudio.app, and the applicable upstream acknowledgments. Section 4(d) permits these notices in a distributed NOTICE file, accompanying source or documentation, or an appropriate third-party notices display.
  • Retain applicable copyright and attribution notices in source-form derivatives, as required by section 4(c).
  • Mark modified files with prominent notices stating that they were changed, as required by section 4(b).

Your application or engine may use its own product name. Renaming or repackaging does not remove applicable license and attribution obligations; preserve the Nara Mini v1 identity in the required attribution notices.

Recommended additional wording for an About or model-information screen:

Uses Nara Mini v1 by Nara contributors, a Kokoro-based Burmese and English speech model. https://naraaudio.app β€” https://huggingface.co/YeeNyunn/nara-mini-v1 Licensed under Apache 2.0; see the accompanying LICENSE and NOTICE.

This short display text supplements, rather than replaces, the complete applicable notices. This section explains the existing license; it does not add a mandatory product name, advertising credit, or other restriction beyond Apache 2.0. The LICENSE and NOTICE remain unchanged.

Downloads last month
320
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Spaces using YeeNyunn/nara-mini-v1 3