Discover @kaiidams Open Source projects

Katsuya Iida (@kaiidams)

kaiidams

Stars
139
Global Rank 162,945 (Top 6 %)
Followers 22
Following 7
Registered almost 7 years ago
Most used languages

C#
42.9 %

Python
42.9 %

C
14.3 %
Location 🇯🇵 Japan
Country Total Rank 4,871
Country Ranking

C#
472

Python
603

C
921

Kokoro-Speech-Dataset

A public domain single speaker Japanese speech dataset

soundstream-pytorch

Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint

voice100

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.

FreeHand-Dataset

Synthesized hand pose images generated by Blender

NeMoOnnxSharp

Text-to-speech and speech recognition, VAD with NVIDIA NeMo and ONNX Runtime for .NET Core.

YamNetUnityDemo

This is prediction demo of TensorFlow YamNet model on Unity Barracuda.

Voice100AndroidApp

Voice100 Android App is a TTS/ASR sample app that uses ONNX Runtime and Voice100 neural TTS/ASR models on Xamarin. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without recursion.

Kokoro-Align

Kokoro-Align is a PyTorch speech-transcript alignment tool for LibriVox. It splits audio files in silent positions and find CTC best path to align transcript texts with the audio files.

TransferLearningAudio

ML.NET porting of https://www.tensorflow.org/tutorials/audio/transfer_learning_audio

Voice100Sharp

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without recursion.

LanguageDetection

C# port of https://github.com/shuyo/language-detection

voice100-runtime

Voice100 runtime. Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without recursion.

Voice100Godot

NeMoOnnxGodot

Neural speech with NVIDIA NeMo and ONNX Runtime