Consuming the obtained inference in production #7
Comments
|
Sure, you can convert our models to ONNX and deploy them with ONNXRuntime. |
|
@SangeethaVenkatesan the gradio demos also have a api if your interested https://hf.space/gradioiframe/NATSpeech/PortaSpeech/api |
Heyy, Thank you for the response! We would like to involve the model in the production pipeline,relying on gradio api would'nt be a production ready solution, since we have to consider rate limit in production api request calls coming in for the model to infer. Would it be possible if it could be placed in hugging_face model hub, so the inference would be a pretty standard procedure and also reliable in production. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello Team,
Amazing model, very good sample results. I would like to know how as the team looking to use the model results in our production application. We would like to use the obtained inference in production. Huggingface there is only demo on gradio. But we would like to implement this model results in our production pipeline, Please let me know how we can go about it!
The text was updated successfully, but these errors were encountered: