elbruno/Qwen3-TTS-12Hz-0.6B-CustomVoice-ONNX

By elbruno · ↓ 0 · ♥ 3 · Updated 2026-02-22

What's in this repo

This page lists the files in elbruno/Qwen3-TTS-12Hz-0.6B-CustomVoice-ONNX, including code_predictor.onnx, talker_decode.onnx, talker_prefill.onnx and more.

4 ONNX models (.onnx files)
35 files, including 22 .npy, 4 .onnx, 3 .json, 3 .data, 1 .md, 1 .txt
Last updated 2026-02-22

ONNX files

File	Size	Download
code_predictor.onnx	—	Download
talker_decode.onnx	—	Download
talker_prefill.onnx	—	Download
vocoder.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Qwen3-TTS 12Hz 0.6B CustomVoice — ONNX

ONNX export of Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice for local inference with C# / ONNX Runtime.

Files

File	Description	Size
`talker_prefill.onnx` + `.data`	Talker LM prefill (28 layers)	~1.7 GB
`talker_decode.onnx` + `.data`	Talker LM single-step decode	~1.7 GB
`code_predictor.onnx`	Code Predictor (5 layers, 15 groups)	~420 MB
`vocoder.onnx` + `.data`	Vocoder decoder (24kHz output)	~437 MB
`embeddings/`	Text/codec embeddings as .npy + config	~1.4 GB
`tokenizer/`	BPE tokenizer (vocab.json, merges.txt)	~4 MB

Usage with C#

# Clone the app repo
git clone https://github.com/elbruno/qwen-labs-cs.git
cd qwen-labs-cs

# Download models
python python/download_onnx_models.py --repo-id elbruno/Qwen3-TTS-12Hz-0.6B-CustomVoice-ONNX

# Run
dotnet run --project src/QwenTTS -- --model-dir python/onnx_runtime --text "Hello world" --speaker ryan --language english

Architecture

Talker: 28 transformer layers, 16 attn heads, 8 KV heads, hidden=1024
Code Predictor: 5 layers, generates codebook groups 1-15
Vocoder: RVQ dequantize → transformer → BigVGAN decoder, 12Hz → 24kHz (1920× upsample)
KV Cache: Decode uses stacked format (num_layers, B, num_kv_heads, T, head_dim)
Speakers: serena, vivian, uncle_fu, ryan, aiden, ono_anna, sohee, eric, dylan

License

Apache-2.0 (same as base model)

Model info

text-to-speech

onnx tts qwen3-tts text-to-speech base_model:Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice base_model:quantized:Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice license:apache-2.0 region:us

↓ 0 ♥ 3

Created: 2026-02-21

Updated: 2026-02-22

View on Hugging Face

Files (35)

.gitattributes

README.md

code_predictor.onnx ONNX

embeddings/codec_head_weight.npy

embeddings/config.json

embeddings/cp_codec_embedding_0.npy

embeddings/cp_codec_embedding_1.npy

embeddings/cp_codec_embedding_10.npy

embeddings/cp_codec_embedding_11.npy

embeddings/cp_codec_embedding_12.npy

embeddings/cp_codec_embedding_13.npy

embeddings/cp_codec_embedding_14.npy

embeddings/cp_codec_embedding_2.npy

embeddings/cp_codec_embedding_3.npy

embeddings/cp_codec_embedding_4.npy

embeddings/cp_codec_embedding_5.npy

embeddings/cp_codec_embedding_6.npy

embeddings/cp_codec_embedding_7.npy

embeddings/cp_codec_embedding_8.npy

embeddings/cp_codec_embedding_9.npy

embeddings/speaker_ids.json

embeddings/talker_codec_embedding.npy

embeddings/text_embedding.npy

embeddings/text_projection_fc1_bias.npy

embeddings/text_projection_fc1_weight.npy

embeddings/text_projection_fc2_bias.npy

embeddings/text_projection_fc2_weight.npy

talker_decode.onnx ONNX

talker_decode.onnx.data

talker_prefill.onnx ONNX

talker_prefill.onnx.data

tokenizer/merges.txt

tokenizer/vocab.json

vocoder.onnx ONNX

vocoder.onnx.data

Related models

More text-to-speech models

Browse all text-to-speech models