funkgeek Goto Github PK

nlpnote

Gitbook Address: https://app.gitbook.com/@nlpgroup/s/nlpnote/

python-beat-detector

Real-time detection of beats for audio, calculates BPM and flashes LED strip in time with music.

pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

raplyrics

"Source code" for this video: https://www.youtube.com/watch?v=a0EyfdQ0QTQ I'm only adding 1 file here bc I didn't actually code that much.

real-time-voice-cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

sinsy

Neural network-based singing voice synthesis library for research

sinsy-remix

The HMM-Based Singing Voice Syntheis System Remix "Sinsy-r"

sklearn-doc-zh

:book: [译] scikit-learn（sklearn） 中文文档

sp2si-code

Contains code for our work on speech to singing conversion (ICASSP 2020)

speaking-clock

A speak clock(concatenative speech synthesis) that tell you the current time

speech-conversion-between-different-modalities

Generative Adversarial Networks for different impaired speech conversions

speech-signal-processing

several snippet of different speech signal processing code

speechsplit

Unsupervised Speech Decomposition Via Triple Information Bottleneck

spoken-digit-recognition

Recognize English spoken digits using Hidden Markov Model

tacotron

tacotron for research on Chinese speech synthesis and Taiwanese speech synthesis from Chinese input text sequence with different granularities

tacotron2-mandarin

Tensorflow implementation of Chinese/Mandarin TTS (Text-to-Speech) based on Tacotron-2 model.

tacotronv2_wavernn_chinese

tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)

tensorflow_practice

tensorflow实战练习，包括强化学习、推荐系统、nlp等

tensorflowtts

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

uberduck-ml-dev

ML models for Uberduck

voice-conversion-using-deep-neural-networkswith-speaker-independent-pre-training----dnn_vcc

This is first ever DNN using pretaining for Voice conversion.

vowel_space_plot

wave-u-net-for-speech-enhancement

Improved speech enhancement with the Wave-U-Net, a deep convolutional neural network architecture for audio source separation, implemented for the task of speech enhancement in the time-domain.

wave-u-net-for-speech-enhancement-1

Implement Wave-U-Net by PyTorch, and migrate it to the speech enhancement.