Downloads · 30 days
47
20% of all-time downloads
qwen3-tts-tokenizer-multi-codebook-hf
shahvandit/qwen3-tts-tokenizer-multi-codebook-hf
qwen3-tts-tokenizer-multi-codebook-hf is a feature extraction model from shahvandit. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
Conversion of the Qwen3-TTS multi-codebook (12Hz) speech tokenizer to the Transformers implementation added in huggingface/transformers44517. Stored in float32, matching the original.
All-time downloads
232
Public
Parameters
171M
682 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors682 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_tts_tokenizer_multi_codebook
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Sep 16, 2026
- SHA
- a818c404
Base models
Model card
From the Hugging Face model README
Qwen3-TTS multi-codebook tokenizer (Transformers conversion)
Conversion of the Qwen3-TTS multi-codebook (12Hz) speech tokenizer to the Transformers implementation added in huggingface/transformers#44517. Stored in float32, matching the original.
Converted from Qwen/Qwen3-TTS-Tokenizer-12Hz with the conversion script that
ships with the model. The tensors are unchanged: conversion only renames state dict keys to match the
Transformers module layout, fuses the code predictor's per-group lm_head layers into one projection,
and rewrites the configuration.
This checkpoint exists so the integration tests have something to fetch while the model is under review. Once merged, a Transformers-compatible checkpoint is expected to be hosted by the Qwen team.
Usage
from transformers import Qwen3TTSTokenizerMultiCodebookModel
model = Qwen3TTSTokenizerMultiCodebookModel.from_pretrained("shahvandit/qwen3-tts-tokenizer-multi-codebook-hf")
License
Apache 2.0, inherited from the original model.
- Task
- Feature Extraction
- Library
- transformers
- Type
- qwen3_tts_tokenizer_multi_codebook
- License
- apache-2.0
- Created
- Aug 18, 2026
- Updated
- Sep 16, 2026