Singapore

Feiteng

Elite
@lifeiteng

Full stack Algorithm Engineer

x.com/FeitengLi

vall-e. PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

2.2k

OmniSenseVoice. Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

897

naturalspeech3_facodec. FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

251

codingmath. Tech

82

SoundStorm.

71

NotebookTTS. Text-To-Speech for NotebookLM

39

Aligner-SUPERB. Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark

38

FasterDNN. Faster Deep Neural Networks

37

NaturalSpeech2.

33

TF_SpeechRecoChallenge. solutions for https://www.kaggle.com/c/tensorflow-speech-recognition-challenge

31

TTS-TextAnalyzer. TTS Text Analyzer

31

VoiceBox. Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

28

Rabbit. Explore Text-To-Speech

25

Optimizers. Tensorflow Optimizers

11

easySVM. 五行代码实现一个SVM

8

TopicsInASR. Topics in Automatic Speech Recognition

6

encodec. Python

4

audiossl. A library built for easier audio self-supervised training, downstream tasks evaluation

4

lhotse. Tools for handling speech data in machine learning projects.

3

kaldifeat. Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API

3

descript-audio-codec. State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

2

audio2py. Python

2

audio-ai-timeline. A timeline of the latest AI models for audio generation, starting in 2023!

2

SpeechTokenizer. This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

2

whisperX. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

2

transformers. 🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

2

S3Tokenizer. Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

2

hanziconv. Hanzi Converter for Traditional and Simplified Chinese

2

NeMo. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

2

merlin. This is now the official location of the Merlin project.

1

lis. Python library for finding Longest Increasing Subsequence (LIS) in an integer array

1

OpenBLAS. OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

1

Megatron-LM. Ongoing research training transformer models at scale

1

tts-tutorial. Text-to-Speech tutorial at SLTU 2016

1

warp-ctc. Fast parallel CTC.

1

DeepPhonemizer. Grapheme to phoneme conversion with deep learning.

1

nv-wavenet. Reference implementation of real-time autoregressive wavenet inference

1

DiscoSeqSampler. Distributed Coordinated Sequence Sampler

1

reverb. Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

1

tensor2tensor. A library for generalized sequence to sequence models

1

lame. unofficial LAME MP3 Encoder

1

sebbs. Prediction of sound event bounding boxes (SEBBs)

1

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

1

seq2seq-1. A general-purpose encoder-decoder framework for Tensorflow

1

io. Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

1
45
Apply