Metadata-Version: 2.4
Name: ttsdb_e2_tts
Version: 0.1.2
Summary: E2 TTS model for TTSDB
Requires-Python: <=3.14,>=3.10
Requires-Dist: accelerate>=0.33.0
Requires-Dist: bitsandbytes>0.37.0
Requires-Dist: cached-path
Requires-Dist: click
Requires-Dist: datasets
Requires-Dist: einops
Requires-Dist: ema-pytorch>=0.5.2
Requires-Dist: gradio>=3.45.2
Requires-Dist: huggingface-hub
Requires-Dist: jieba
Requires-Dist: librosa
Requires-Dist: matplotlib
Requires-Dist: numba==0.63.1
Requires-Dist: numpy<=1.26.4
Requires-Dist: pydub
Requires-Dist: pypinyin
Requires-Dist: safetensors
Requires-Dist: soundfile
Requires-Dist: tomli
Requires-Dist: torch>=2.0.0
Requires-Dist: torchaudio>=2.0.0
Requires-Dist: torchdiffeq
Requires-Dist: tqdm>=4.65.0
Requires-Dist: transformers
Requires-Dist: transformers-stream-generator
Requires-Dist: ttsdb-core>=0.1.2
Requires-Dist: vocos
Requires-Dist: wandb
Requires-Dist: x-transformers>=1.31.14
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Description-Content-Type: text/markdown

# E2 TTS

The model description is sourced from `config.yaml` (`metadata.description`).

## Installation

```bash
just setup e2-tts
```

## Usage

```python
from ttsdb_e2_tts import E2TTS

model = E2TTS(model_id="ttsds/e2-tts")
audio, sr = model.synthesize(
    text="Hello, world!",
    reference_audio="path/to/reference.wav"
)
```

## Audio Examples

Generated audio samples from integration tests:

| Language | Text | Audio |
|----------|------|-------|
| English | "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good." | [audio_examples/en_test_001.wav](audio_examples/en_test_001.wav) |
| Chinese | "視野無限廣，窗外有藍天" | [audio_examples/zh_test_001.wav](audio_examples/zh_test_001.wav) |

To regenerate examples, run:
```bash
just test-integration e2-tts
```
