Vagdhenu Ivr Pool Voice
Experimental second voice for Vāgdhenu, fine-tuned on a pooled set of 4 male speakers from IndicVoices-R (gated HF dataset — anyone retraining from scratch must accept its terms separately). Unlike the project's...
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 1,26 GB
- Versión
- vVoice ivr pool 2026 07 ema
- Actualizado
- 19 oct 2026
- Fuente
- Hugging Face
Descripción de la fuente
Vāgdhenu — experimental IVR-pool voice
Experimental second voice for Vāgdhenu, fine-tuned on a pooled set of 4 male speakers from IndicVoices-R (gated HF dataset — anyone retraining from scratch must accept its terms separately). Unlike the project's default chant voice, this checkpoint clones the identity of whatever reference clip it's given.
Trade-off: it reads Sanskrit in a spoken style rather than the traditional chant (pārāyaṇa) cadence — expected, since IndicVoices-R is spoken, not chanted, speech.
voice_ivr_pool_2026-07_ema.pt — EMA-only weights, same format as the project's other DiT voice
checkpoints (ema_model_state_dict key), 60 epochs / 9720 updates on Kaggle T4×2.
Not affiliated with the upstream prathoshap/vagdhenu repo/weights — kept separate since this is
still experimental and trained on gated data with its own license terms.
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 19 oct
Artefactos del modelo
1 artefacto
Artefactos del modelo
1 artefactoExtractos de fuentes
2 extractos
Extractos de fuentes
2 extractos--- tags: - text-to-speech - sanskrit --- # Vāgdhenu — experimental IVR-pool voice Experimental second voice for [Vāgdhenu](https://github.com/prathoshap/vagdhenu), fine-tuned on a pooled set of 4 male speakers from **IndicVoices-R** (gated HF dataset — anyone retraining from scratch must accept its terms separately). Unlike the project's default chant voice, this checkpoint clones the identity of whatever reference clip it's given. Trade-off: it reads Sanskrit in a spoken style rather than the traditional chant (pārāyaṇa) cadence — expected, since IndicVoices-R is spoken, not chanted, speech. `voice_ivr_pool_2026-07_ema.pt` — EMA-only weights, same format as the project's other DiT voice checkpoints (`ema_model_state_dict` key), 60 epochs / 9720 updates on Kaggle T4×2. Not affiliated with the upstream `prathoshap/vagdhenu` repo/weights — kept separate since this is still experimental and trained on gated data with its own license terms.
Source context: 0 downloads · 0 likes · Pipeline text-to-speech · Repo Sharkyyyx28/vagdhenu-ivr-pool-voice
