---
license: other
license_name: see-upstream-and-bundled-license
license_link: https://huggingface.co/IndexTeam/IndexTTS-1.5
base_model: IndexTeam/IndexTTS-1.5
pipeline_tag: text-to-speech
tags:
  - text-to-speech
  - zero-shot-tts
  - voice-cloning
  - machine-unlearning
  - speaker-unlearning
  - cond-id
  - reproducibility
  - mirror
---

# IndexTTS-1.5 — pinned mirror for cond-ID

An **unmodified, commit-pinned mirror** of
[`IndexTeam/IndexTTS-1.5`](https://huggingface.co/IndexTeam/IndexTTS-1.5), bundled with the
matching `index-tts` source tree, so the cond-ID paper's IndexTTS results stay reproducible.

> ⚠️ **Licensing — read before use.** Upstream `IndexTeam/IndexTTS-1.5` is tagged
> `apache-2.0` on the Hub, but the bundled `index-tts-src/LICENSE` is the
> **bilibili Model Use License Agreement**, which carries its own restrictions.
> These are not the same terms. Review both, and defer to upstream, before any use
> beyond research.

## What this is

| | |
|---|---|
| Upstream | [`IndexTeam/IndexTTS-1.5`](https://huggingface.co/IndexTeam/IndexTTS-1.5) |
| Pinned commit | `25851a6036dfd3095bb70fb3c8f49217104672c3` |
| Modifications | **None** to the weights. Adds a vendored `index-tts-src/` tree. |
| Purpose | Reproducibility anchor for the cond-ID paper |

This is the *base* checkpoint that cond-ID edits — **not** an unlearned model.

## Files

```
gpt.pth                     GPT backbone (1.17 GB)
bigvgan_generator.pth       BigVGAN vocoder generator (536 MB)
bigvgan_discriminator.pth   BigVGAN discriminator (1.65 GB, training only —
                            not needed for inference)
dvae.pth                    discrete VAE (243 MB)
bpe.model                   tokenizer
config.yaml                 model config
index-tts-src/              vendored upstream index-tts source tree
```

`bigvgan_discriminator.pth` is mirrored only for completeness with upstream; inference
never loads it. Skip it to save ~1.65 GB:

```python
from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="RootAccess4Life/cond-id-indextts-1.5",
    local_dir="models/index_tts",
    ignore_patterns=["bigvgan_discriminator.pth", "index-tts-src/*"],
)
```

Then:

```bash
export CD_INDEXTTS_DIR=models/index_tts
python scripts/run_eval.py --config configs/indextts.yaml
```

IndexTTS needs its own isolated environment; the repo automates that with
`bash scripts/setup_indextts.sh`.

## Why IndexTTS-1.5 in this paper — and an honest caveat

IndexTTS-1.5 is architecturally the most distinct of the three backbones: autoregressive
but **perceiver-conditioned**, with a BigVGAN vocoder. It is the strongest test of whether
cond-ID is genuinely host-independent rather than tuned to one conditioning design.

**Erasure on IndexTTS is partial.** BigVGAN carries its own speaker encoder, which is a
second identity path that a conditioning-path edit does not touch. cond-ID erases what
flows through the conditioning path; residual identity can still leak through the vocoder.
This is reported as a limitation in the paper rather than smoothed over.

## Related

- 💻 Code: https://github.com/pujariaditya/cond-id-tts-unlearning
- 🔇 Live demo: https://huggingface.co/spaces/RootAccess4Life/cond-id-demo
- 🎧 Audio samples: https://huggingface.co/datasets/RootAccess4Life/cond-id-samples
- 📦 XTTS-v2 mirror: https://huggingface.co/RootAccess4Life/cond-id-xtts-v2

## Citation

```bibtex
@misc{pujari_condid,
  title  = {cond-ID: Conditioning-Space Identity Redirection for Speaker Unlearning in Zero-Shot TTS},
  author = {Pujari, Aditya and Rattani, Ajita},
  note   = {Preprint},
}
```

Please also cite IndexTTS upstream. All credit for these weights belongs to IndexTeam.