---
tags:
- espnet
- audio
- text-to-speech
language: 
- en
datasets:
- libritts
license: cc-by-4.0
inference: false
---

## TTS model - ProDiff with GST + X-Vector

**No support given.**

### Details

```
num_iters_per_epoch: 250
max_epoch: 800
batch_bins: 8000000
tts_conf: 
    spk_embed_dim: 192
```