Downloads · 30 days
43
7% of all-time downloads
aguken-ai/Qwen-3-TTS-12Hz-0.6B-Base-hi-LoRA-Finetuned-BNB-NF4
Qwen-3-TTS-12Hz-0.6B-Base-hi-LoRA-Finetuned-BNB-NF4 is a text-to-speech model from aguken-ai. Use it when you need text read aloud. It is set up for transformers. The card lists the license as apache-2.0.
A Hindi (hi) LoRA finetune of Qwen/Qwen3-TTS-12Hz-0.6B-Base, with the LoRA adapter merged into the base weights and the result quantized to 4-bit NF4 using bitsandbytes.
Downloads · 30 days
43
7% of all-time downloads
All-time downloads
611
Public
Parameters
915M
3.7 GB on disk
Likes
10
Public
Click a slice to open those files.
.safetensors2.6 GB · 100%
From the Hugging Face model README
A Hindi (hi) LoRA finetune of Qwen/Qwen3-TTS-12Hz-0.6B-Base, with the LoRA adapter merged into the base weights and the result quantized to 4-bit NF4 using bitsandbytes.
The base Qwen3-TTS family ships with 10 built-in languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian) but does not include Hindi. This checkpoint extends the base model toward Hindi speech synthesis and voice cloning while keeping the memory footprint small enough to run on consumer GPUs.
| Base model | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| Architecture | Qwen3TTSForConditionalGeneration (discrete multi-codebook LM talker + code predictor) |
| Parameters | ~0.6B (talker), plus speech tokenizer |
| Target language | Hindi (hi) |
| Finetuning method | LoRA (adapter merged into base) |
| Quantization | bitsandbytes 4-bit NF4, double quantization, bfloat16 compute dtype |
| Speech tokenizer | Qwen3-TTS-Tokenizer-12Hz (12.5 Hz frame rate, 24 kHz audio) |
| Sample rate | 24 kHz |
| License | Apache-2.0 (inherited from base) |
The following modules are kept in higher precision (not quantized) for output quality: text_projection, codec_head, code_predictor, speaker_encoder.
config.json # Model + quantization config
generation_config.json # Default sampling params
model.safetensors # 4-bit NF4 quantized weights (~1.2 GB)
merges.txt / vocab.json # Text tokenizer
tokenizer_config.json
preprocessor_config.json
speech_tokenizer/ # Qwen3-TTS-Tokenizer-12Hz (encode/decode audio)
conda create -n qwen3-tts python=3.12 -y
conda activate qwen3-tts
pip install -U qwen-tts
pip install -U bitsandbytes # required to load the 4-bit weights
# Optional, for faster inference on supported GPUs:
pip install -U flash-attn --no-build-isolation
The quantization settings are stored in config.json, so the 4-bit weights load automatically — no extra BitsAndBytesConfig is needed.
import torch
import soundfile as sf
from qwen_tts import Qwen3TTSModel
MODEL_ID = "<your-username>/Qwen-3-TTS-12Hz-Base-hi-LoRA-Finetuned-BNB-NF4"
# or a local path to this folder
model = Qwen3TTSModel.from_pretrained(
MODEL_ID,
device_map="cuda:0",
attn_implementation="flash_attention_2", # drop if flash-attn is not installed
)
# Short Hindi reference clip + its transcript for cloning
ref_audio = "path/to/reference_hindi.wav"
ref_text = "नमस्ते, मेरा नाम आरव है और मुझे संगीत सुनना बहुत पसंद है।"
wavs, sr = model.generate_voice_clone(
text="आज मौसम बहुत सुहाना है, चलिए थोड़ी देर बाहर टहलने चलते हैं।",
language="Hindi",
ref_audio=ref_audio,
ref_text=ref_text,
)
sf.write("output_hindi_clone.wav", wavs[0], sr)
import torch
from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
device_map="cuda:0",
trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
| Method | LoRA, adapter merged into base weights |
| Target language | Hindi (hi) |
| LoRA rank / alpha / dropout | TBD |
| Target modules | TBD |
| Training data | TBD |
| Epochs / steps | TBD |
| Optimizer / LR / schedule | TBD |
| Hardware | TBD |
This work builds on Qwen3-TTS by the Qwen team at Alibaba Cloud.
@article{Qwen3-TTS,
title={Qwen3-TTS Technical Report},
author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
journal={arXiv preprint arXiv:2601.15621},
year={2026}
}