Model reference · open weights
qwen3-tts-tokenizer-12hz is an open-weight audio or speech model from cstr, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Qwen3-TTS Tokenizer 12Hz — GGUF (CrispASR) GGUF / ggml conversions of Qwen/Qwen3-TTS-Tokenizer-12Hz for use with the qwen3-tts backend in CrispStrobe/CrispASR. Qwen3-TTS-Tokenizer-12Hz is the separate speech tokenizer / codec used by the Qwen3-TTS family: - 10 supported languages: zh en ja ko de fr ru pt es it - 12.5 Hz, 16-codebook speech representation - used for reference-audio encoding, voice-pack baking, and final waveform decode - Apache-2.0 licence This repo contains the tokenizer / codec only. Use it together with the talker GGUF from cstr/qwen3-tts-0.6b-base-GGUF. Files File | Size | Notes qwen3-tts-tokenizer-12hz.gguf | 342 MB | F16 qwen3-tts-tokenizer-12hz-q80.gguf | 277 MB | Q80 codec quant Quick Start The tokenizer GGUF is used for: - encoding reference audio into refcode - baking / loading voice-pack GGUFs - decoding generated codes back into 24 kHz mono WAV Quantisation Notes Current CrispASR validation status: - qwen3-tts-tokenizer-12hz.gguf - reference baseline - qwen3-tts-tokenizer-12hz-q80.gguf - usable, but numerically less faithful than the F16 codec in strict diff tests For best fidelity, keep the tokenizer / codec at F16 even when quantising the talker. In current CrispASR testing, codec quantisation drifts earlier in the codec-encoder path than talker-only quantisation. This repo may also publish lower-bit talker variants in the companion talker repo. If you use them, the safest pairing is still: - quantised talker - qwen3-tts-tokenizer-12hz.gguf kept at F16 In other words: if you must choose where to keep precision, keep it in the tokenizer / codec first. How this was made 1. The upstream tokenizer / codec checkpoint was converted to GGUF F16 by models/convert-qwen3-tts-tokenizer-to-gguf.py. 2. Quantised variants are produced with CrispASR's GGUF quantiser. 3. Encode / decode inference is implemented in src/qwen3tts.cpp, sharing the same runtime as the qwen3-tts talker backend. Reference implementation Architecture and behaviour were checked against the official Qwen release: - upstream tokenizer model card: Qwen/Qwen3-TTS-Tokenizer-12Hz - upstream repository: QwenLM/Qwen3-TTS - technical report: Qwen3-TTS Technical Report Related - Comp
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | cstr |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | ggml |
| Based on | Qwen/Qwen3-TTS-Tokenizer-12Hz |
| Released | 2026-04-29 |
| Popularity | 5k downloads / month |
| Likes | 6 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| qwen3-tts-tokenizer-12hz-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys cstr-qwen3-tts-tokenizer-12hz for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (cstr-qwen3-tts-tokenizer-12hz below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="cstr-qwen3-tts-tokenizer-12hz" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗