|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
Model Usage and Inference |
|
|
|
|
|
These models are fully general-purpose and can be used for any text-to-speech inference scenario. They are not limited to a specific dataset, domain, or pipeline, and they support flexible integration into existing TTS systems or standalone applications. |
|
|
A complete, ready-to-run inference implementation is available here: |
|
|
|
|
|
https://huggingface.co/spaces/thewh1teagle/phonikud-tts |
|
|
|
|
|
The referenced Hugging Face Space contains: |
|
|
* A working inference demo in the browser. |
|
|
* Full inference source code for local execution. |
|
|
* Examples showing how to feed text, speaker information, and configuration parameters. |
|
|
* Instructions for integrating the model into Python-based TTS workflows. |
|
|
|
|
|
These resources ensure that the models can be executed immediately without additional setup and can serve as a reference for custom deployments, API servers, or production TTS pipelines. |
