akreal

netron

Visualizer for neural network, deep learning and machine learning models

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

ivy

The Unified AI Framework

espnet

End-to-End Speech Processing Toolkit

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

mkchromecast

Cast macOS and Linux Audio/Video to your Google Cast and Sonos Devices

pytorch-meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

ecco

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

IMS-Toucan

Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.

chinese_speech_pretrain

chinese speech pretrained models

ru_transformers

PyTorch-Model-Compare

Compare neural networks by their feature similarity

SpeechTransProgress

Tracking the progress in end-to-end speech translation

VBx

Variational Bayes HMM over x-vectors diarization

libriheavy

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

elpis

🙊 software for creating speech recognition models.

gtn

Automatic differentiation with weighted finite-state transducers.

sova-dataset

DNC

Discriminative Neural Clustering for Speaker Diarisation

Voice-Privacy-Challenge-2022

Baseline Recipe for VoicePrivacy Challenge 2022: anonymization systems and evaluation software

TurkicASR

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

bk_clustering

Burj Khalifa Clustering method

speaker-anonymization

Speaker anonymization pipeline for hiding the identity of the speaker of a recording by changing the voice in it.

VoicePAT

VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.

speechcatcher

llama

Inference code for LLaMA 2 models

speechGLUE

SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.

mt-bigscience

Evaluation results for Machine Translation within the BigScience project

zamia-speech

Open tools and data for cloudless automatic speech recognition