ModelVérifiéExterne

IndexTTS2 Kazakh

bilibili-indextts-license

Sourcehuggingface.co/AnuarSv/IndexTTS2-Kazakh/tree/3a93637df4f652c6bacb66e5536b2a49a0290562

TypeOtherModèle de baseIndexTeam/IndexTTS-2VersionRevision 3a93637Éditeur@AnuarSvCClasse

Source du modèle

Type: Other
Taille du fichier: 6,89 GB
Modèle de base: IndexTeam/IndexTTS-2
Version: vRevision 3a93637
Mis à jour: 3 oct. 2026
Éditeur: @AnuarSv
Téléchargements: 3
Source: Hugging Face

Description de la source

IndexTTS2 Kazakh Finetune

Fine-tuned GPT component of IndexTTS2 on Kazakh language data.

Special thanks to Nuraidar Mambetaly and Altair Balakhazy for their collaboration and support throughout this project.

Training Details

Base model: IndexTeam/IndexTTS-2
Dataset: InflexionLab/ISSAI-KSC2-Structured — 4.8GB subset
Hardware: Google Colab A100 40GB
Training: 3 epochs, 912 steps
BPE vocab size: 2000 tokens (Kazakh-specific)

Validated on Tesla V100 16GB. Inference uses approximately 10GB VRAM.

Audio Sample

Text: Менің досымның жақсы және жаман әдеттері бар. Жақсы әдетт ол маған көмектеседі. Ол мені әрқашан қолдайтын болады. Ал жаман әдетті кейде ол менің затымды рұқсатсыз алып кетуі мүмкін. Кейде ол мені ренжітеді. Бірақ артынан менден кешірім сұрайды.

Listen to sample

Training Curves

Training curves

Limitations

The training data contains a single speaker throughout all 4.8GB. Voice cloning does not generalize to other voices at this stage. The model produces Kazakh speech but defaults to the training speaker regardless of the reference audio provided.

This will improve with a multi-speaker dataset. Contributions and experiments are welcome.

Installation

Download the base model first:

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="IndexTeam/IndexTTS-2",
    local_dir="checkpoints"
)

Then replace the GPT checkpoint and tokenizer with the Kazakh versions:

# Download this repo
hf download AnuarSv/IndexTTS2-Kazakh --local-dir kz_files

# Replace
cp kz_files/gpt.pth checkpoints/gpt.pth
cp kz_files/bpe.model checkpoints/bpe.model
cp kz_files/config.yaml checkpoints/config.yaml

Clone the training branch and run:

git clone -b training_v2 https://github.com/JarodMica/index-tts.git
cd index-tts
uv sync --all-extras
uv run webui.py --model_dir checkpoints --fp16

Config Change

The base model uses number_text_tokens: 12000. This finetune uses 2000 to match the Kazakh BPE vocabulary. The config.yaml in this repo already has this applied.

What's in This Repo

File	Description
`gpt.pth`	Fine-tuned GPT checkpoint (Kazakh)
`bpe.model`	SentencePiece BPE tokenizer trained on Kazakh text
`config.yaml`	Model config with `number_text_tokens: 2000`

Files not included (s2mel.pth, feat1.pt, feat2.pt, qwen0.6bemo4-merge) are part of the base model and should be downloaded from IndexTeam/IndexTTS-2.

Sources

1 source

Hugging FacePrincipalVersion 3a93637df4f652c6bacb66e5536b2a49a0290562

huggingface.co/AnuarSv/IndexTTS2-Kazakh/tree/3a93637df4f652c6bacb66e5536b2a49a0290562

Vérifié 10 août

Artefacts du modèle

1 artefact

gpt.pth

pth · 6,89 GB · SHA-256 6abd27f720f4…fa42 · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme11 juil.huggingface.co/AnuarSv/IndexTTS2-Kazakh

--- language: - kk license: other license_name: bilibili-indextts-license license_link: https://huggingface.co/IndexTeam/IndexTTS-2/blob/main/INDEX_MODEL_LICENSE base_model: IndexTeam/IndexTTS-2 base_model_relation: finetune pipeline_tag: text-to-speech tags: - kazakh - indextts - tts datasets: - InflexionLab/ISSAI-KSC2-Structured --- # IndexTTS2 Kazakh Finetune Fine-tuned GPT component of [IndexTTS2](https://github.com/index-tts/index-tts) on Kazakh language data. Special thanks to **Nuraidar Mambetaly** and **Altair Balakhazy** for their collaboration and support throughout this project. ## Training Details - **Base model:** [IndexTeam/IndexTTS-2](https://huggingface.co/IndexTeam/IndexTTS-2) - **Dataset:** [InflexionLab/ISSAI-KSC2-Structured](https://huggingface.co/datasets/InflexionLab/ISSAI-KSC2-Structured) — 4.8GB subset - **Hardware:** Google Colab A100 40GB - **Training:** 3 epochs, 912 steps - **BPE vocab size:** 2000 tokens (Kazakh-specific) Validated on Tesla V100 16GB. Inference uses approximately 10GB VRAM. ## Audio Sample Text: `Менің досымның жақсы және жаман әдеттері бар. Жақсы әдетт ол маған көмектеседі. Ол мені әрқашан қолдайтын болады. Ал жаман әдетті кейде ол менің затымды рұқсатсыз алып кетуі мүмкін. Кейде ол мені ренжітеді. Бірақ артынан менден кешірім сұрайды.` [Listen to sample](https://huggingface.co/AnuarSv/IndexTTS2-Kazakh/resolve/main/preview/sample.mp3) ## Training Curves ![Training curves](preview/tenserflow_dashboard.jpg) ## Limitations The training data contains a single speaker throughout all 4.8GB. Voice cloning does not generalize to other voices at this stage. The model produces Kazakh speech but defaults to the training speaker regardless of the reference audio provided. This will improve with a multi-speaker dataset. Contributions and experiments are welcome. ## Installation Download the base model first: ```python from huggingface_hub import snapshot_download snapshot_download( repo_id="IndexTeam/IndexTTS-2", local_dir="checkpoints" ) ``` Then replace the GPT checkpoint and tokenizer with the Kazakh versions: ```bash # Download this repo hf download AnuarSv/IndexTTS2-Kazakh --local-dir kz_files # Replace cp kz_files/gpt.pth checkpoints/gpt.pth cp kz_files/bpe.model checkpoints/bpe.model cp kz_files/config.yaml checkpoints/config.yaml ``` Clone the training branch and run: ```bash git clone -b...

Note17 juil.huggingface.co/AnuarSv/IndexTTS2-Kazakh

Source context: 3 downloads · 3 likes · Pipeline text-to-speech · Repo AnuarSv/IndexTTS2-Kazakh

Note11 juil.huggingface.co/AnuarSv/IndexTTS2-Kazakh

Source context: 2 downloads · 3 likes · Pipeline text-to-speech · Repo AnuarSv/IndexTTS2-Kazakh