Downloads · 30 days
360
47% of all-time downloads
Abduqayum/uzbek-tts-natural-speech-chatterbox
uzbek-tts-natural-speech-chatterbox is a text-to-speech model from Abduqayum. Use it when you need text read aloud. It is set up for chatterbox. The card lists the license as mit.
A LoRA fine-tune of ResembleAI/chatterbox (Standard/non-Turbo) for Uzbek speech synthesis, trained on ~30 hours of single-speaker Uzbek audiobook narration.
Downloads · 30 days
360
47% of all-time downloads
All-time downloads
762
Public
Repo size
2.1 GB
Likes
3
Public
Click a slice to open those files.
.safetensors2.1 GB · 100%
From the Hugging Face model README
A LoRA fine-tune of ResembleAI/chatterbox (Standard/non-Turbo) for Uzbek speech synthesis, trained on ~30 hours of single-speaker Uzbek audiobook narration.
The LoRA adapter has been merged into the base model, so these are standalone T3 weights —
no PEFT required at inference time. The model also supports zero-shot voice cloning: pass
any reference wav and it will speak your text in that voice.
<audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/tts_demo/sample1.wav"></audio> <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/tts_demo/sample2.wav"></audio> <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/tts_demo/sample3.wav"></audio> <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/tts_demo/sample4.wav"></audio> <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/tts_demo/sample5.wav"></audio>
Bobur Akmalov <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/voice_cloning_demo/Bobur%20Akmalov.wav"></audio>
Davron Fayziyev <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/voice_cloning_demo/Davron%20Fayziyev.wav"></audio>
Jennifer Lawrence <audio controls src="https://huggingface.co/Abduqayum/uzbek-tts-natural-speech-chatterbox/resolve/main/samples/voice_cloning_demo/Jennifer%20Lawrence.wav"></audio>
| File | Description |
|---|---|
t3_finetuned_merged.safetensors | Standalone fine-tuned T3 (speech-token AR model), LoRA merged in |
tokenizer.json | Grapheme tokenizer, 2454 tokens (unchanged from base — Standard mode uses a fixed multilingual grapheme vocab that already covers Uzbek Latin script) |
reference_voice.wav | Default reference clip for the fixed training voice |
samples/ | Demo audio (see above) |
inference.py | Standalone script to run synthesis, fixed-voice or cloning |
The s3gen (vocoder) and ve (voice encoder) weights are not re-uploaded here since they're
unmodified from the base model — inference.py expects them from a base install (see Usage).
This model was trained with, and is meant to be run through,
gokhaneraslan/chatterbox-finetuning —
the same toolkit used to train it. That repo vendors the Chatterbox model code and gives you
s3gen.safetensors / ve.safetensors / conds.pt via its setup.py.
git clone https://github.com/gokhaneraslan/chatterbox-finetuning.git
cd chatterbox-finetuning
pip install -r requirements.txt
# if you hit a pkg_resources / setuptools ImportError from resemble-perth:
pip install "setuptools<81"
python setup.py # downloads base s3gen/ve/conds + the 2454-token tokenizer
# download this repo's files into the toolkit root (or anywhere, and pass paths as flags):
huggingface-cli download <this-repo-id> --local-dir uzbek_chatterbox
cp uzbek_chatterbox/inference.py .
Fixed voice:
python inference.py \
--text "Salom, bugungi kunda sun'iy intellekt texnologiyalari juda tez rivojlanmoqda." \
--audio_prompt uzbek_chatterbox/reference_voice.wav \
--merged_weights uzbek_chatterbox/t3_finetuned_merged.safetensors \
--output out.wav
Voice cloning (swap in any reference wav):
python inference.py \
--text "Salom, qandaysiz?" \
--audio_prompt path/to/some_other_voice.wav \
--merged_weights uzbek_chatterbox/t3_finetuned_merged.safetensors \
--output out.wav
Text of any length is handled — inference.py splits long input into sentence-sized chunks
internally (a single generate() call is capped at 1000 speech tokens and can otherwise cut off
mid-word on long paragraphs).
See TRAINING.md for the full step-by-step recipe (dataset format, exact config, commands) to reproduce this fine-tune on your own dataset/language.
MIT, inherited from the base ResembleAI/chatterbox model. The training toolkit (gokhaneraslan/chatterbox-finetuning) is Apache 2.0.