Swar: open Nepali voice cloning

Swar speaks Nepali the way it is spoken in Nepal and clones a voice from 20 to 30 seconds of someone talking. It reads Nepali, English, and Nepali mixed with English. By Naamche Labs.

Try it free: Colab notebook (free T4 GPU). Code and paper: github.com/Naamche-Labs/swar. Listening test: swar-vote.vercel.app.

Files

• podvoices_ema.pt: the model (F5-TTS Base architecture, EMA weights).
• vocab.txt: character vocabulary (IndicF5).
• kriti_onnx/: Kriti, our Nepali speech recogniser (MIT), used to transcribe uploads and check takes.
• presets/: ready voices Maya (female) and Aarav (male), built only from model-made audio.
• app/: the cloner app (Gradio) used by the notebook.

Results (NepTTS-Bench, 205 sentences, one take)

System	Character error	Pronunciation error	UTMOS
Swar, studio voice	6.19	2.92	3.82
Swar, Maya voice	7.45	4.52	4.09
OmniVoice (same prompt)	6.68	4.32	3.93
Indic-Speak Srijana	10.25	8.12	3.97
ElevenLabs v3	15.70	12.91

FLEURS cloning of unseen speakers: CER 4.55, speaker similarity 0.691, UTMOS 2.67 (OmniVoice 5.30, 0.681, 2.49). UTMOS is an automatic predictor, not a listener test.

Training data

Initialised from ai4bharat/IndicF5 (MIT). Fine-tuned on AI4Bharat Rasa and IndicVoices-R (CC BY 4.0), Google FLEURS (CC BY 4.0), OpenSLR 43 and 54 (CC BY-SA 4.0), LibriTTS-R (CC BY 4.0), and podcast speech used with the speakers' permission (not released). The weights are released under CC BY-SA 4.0 to respect the share-alike data.

Responsible use

Only clone a voice with that person's permission. Do not use Swar to impersonate anyone, to deceive, or to commit fraud.