Downloads · 30 days
50
16% of all-time downloads
phoonnx-indic-parler
OpenVoiceOS/phoonnx-indic-parler
phoonnx-indic-parler is a text-to-speech model from OpenVoiceOS. Use it when you need text read aloud. It is set up for onnx. The card lists the license as apache-2.0.
ONNX export of ai4bharat/indic-parler-tts for the phoonnx indicparler engine.
All-time downloads
313
Public
Repo size
5.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx5.2 GB · 99%
At a glance
- Task
- Text-to-Speech
- Library
- onnx
- License
- apache-2.0
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- 6c4faee5
Base models
Model card
From the Hugging Face model README
phoonnx — Indic Parler-TTS (ONNX)
ONNX export of ai4bharat/indic-parler-tts
for the phoonnx indic_parler engine.
Indic Parler-TTS speaks 20 Indic languages and English. You select the voice with a natural-language description ("Rohit's voice is clear and expressive..."), not with a speaker id or a reference clip.
Graphs
| File | Size | Purpose |
|---|---|---|
text_encoder.onnx | 1.4 GB | Flan-T5 encoder over the voice description |
decoder_prefill.onnx | 2.1 GB | First AR step; emits self-attention and cross-attention KV |
decoder_decode.onnx | 1.3 GB | Later AR steps; consumes both caches, emits self-attention KV only |
dac_decoder.onnx | 217 MB | DAC 44.1 kHz codec decoder (9 codebooks) |
tokenizer.json | prompt tokenizer (the text you want spoken) | |
description_tokenizer.json | description tokenizer (Flan-T5 vocabulary) | |
config.json | self-describing phoonnx config (engine: indic_parler) |
The two tokenizers are different vocabularies. Upstream is explicit about this: one tokenizer for the prompt, one for the description.
Architecture
description --> Flan-T5 encoder --> encoder states --> cross-attention (all 24 layers)
prompt --> embed_prompts --> prepended to the decoder input embeddings
decoder --> 9 delayed DAC codebooks --> DAC decoder --> 44.1 kHz mono
Cross-attention keys and values do not change while decoding, so decoder_prefill
computes them once and decoder_decode reads them back unchanged.
Parity
Every graph is float32 and was checked against the PyTorch model
(parler_tts.ParlerTTSForConditionalGeneration, eager attention) on ser9 CPU:
| Check | Result |
|---|---|
| Text encoder, max abs diff (hi / en / ta) | 3.9e-07 / 6.5e-06 / 3.2e-07 |
| Prefill KV, max abs diff (self K/V, cross K/V) | 8.1e-06 / 4.5e-06 / 2.4e-06 / 1.2e-06 |
| Greedy codes, 60 steps | identical, all 3 languages |
| Waveform correlation vs torch | 0.9999999917 / 1.0000000000 / 1.0000000000 |
| Waveform RMSE vs torch | 1.3e-08 / 5.0e-08 / 1.5e-08 |
No quantised variants are published: the quantised graphs were not verified, and phoonnx does not ship unverified exports.
Notice
Upstream model: ai4bharat/indic-parler-tts by AI4Bharat,
built on huggingface/parler-tts by Yoach
Lacombe, Vaibhav Srivastav and Sanchit Gandhi. Apache-2.0, preserved from upstream.
The DAC codec is Descript's, as vendored by upstream.
The weights are unmodified: the export wraps the PyTorch modules and traces them. No surgery, no quantisation.
- Task
- Text-to-Speech
- Library
- onnx
- License
- apache-2.0
- Languages
- as, bn, brx, doi, en, gu
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026