Update README.md
Browse files
README.md
CHANGED
|
@@ -25,4 +25,12 @@ Older versions of the runtime may not work with these files.
|
|
| 25 |
|
| 26 |
The models are intended to be used within the React Native ExecuTorch package. If you want to use them outside the package,
|
| 27 |
make sure your runtime is compatible with the ExecuTorch version used to export the .pte files and follow the
|
| 28 |
-
[example script](https://github.com/NorbertKlockiewicz/kokoro-export/blob/main/demo/inference_example.py) to run the models.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
The models are intended to be used within the React Native ExecuTorch package. If you want to use them outside the package,
|
| 27 |
make sure your runtime is compatible with the ExecuTorch version used to export the .pte files and follow the
|
| 28 |
+
[example script](https://github.com/NorbertKlockiewicz/kokoro-export/blob/main/demo/inference_example.py) to run the models.
|
| 29 |
+
|
| 30 |
+
## Repository Structure
|
| 31 |
+
|
| 32 |
+
The repository contains 3 main directories:
|
| 33 |
+
- `phonemizer` - data files required by the [Phonemis](https://github.com/IgorSwat/Phonemis) package - responsible for input preprocessing part
|
| 34 |
+
of React Native ExecuTorch Kokoro pipeline.
|
| 35 |
+
- `voices` - a collection of pre-computed speaker embeddings used by the Kokoro model to synthesize speech with specific vocal characteristics.
|
| 36 |
+
- `xnnpack` - exported, XNNPACK-optimized Kokoro runtime modules.
|