Evaluate adding Text2Speech Onnx to speech--audio-processing section

onnx / models

A collection of pre-trained, state-of-the-art models in the ONNX format

http://onnx.ai/models/

Apache License 2.0

8.01k stars 1.41k forks source link

Evaluate adding Text2Speech Onnx to speech--audio-processing section #477

Open GeorgeS2019 opened 3 years ago

GeorgeS2019 commented 3 years ago

Evaluate if the following ONNX address the speech--audio-processing category

stt_en_conv_base_ctc-20210619.onnx
ttsalign_en_conv_base-20210808.onnx
ttsaudio_en_conv_base-20210811.onnx

kaiidams commented 3 years ago

Thank you @GeorgeS2019 for mentioning. For context, voice100 is my personal TTS/ASR project with CNN layers without recursion for embedding in mobile apps Xamarin Android sample . It is not based on research papers. I think it has poor documentation and I am working on it. Please let me know if you have any idea how to improve.

GeorgeS2019 commented 2 years ago

@kaiidams also provides ONNX model for ASR (Automatic Speech Recognition ) based on QuartzNet of NVidia NeMo

The ONNX has been tested in Godot

Check out the readme.md for performance and accuracy!