192 Open source projects that are alternatives of or similar to ser-with-w2v2

A collection of datasets for the purpose of emotion recognition/detection in speech.

A live speech recognition using Facebooks wav2vec 2.0 model.

MelGAN implementation with Multi-Band and Full Band supports...

UniSpeech - Large Scale Self-Supervised Learning for Speech

Keras Implementation of Deepmind's WaveNet for Supervised Learning Tasks

[ICASSP19] An Interaction-aware Attention Network for Speech Emotion Recognition in Spoken Dialogs

A Natural Language Processing course taught by Professor Ghassemi

AdaSpeech: Adaptive Text to Speech for Custom Voice

A Simulation Framework for Auditory Discrimination Experiments

Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Software for interview transcription

Speech-to-text and keyboard input captions for OBS.

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Open source projects related to Snips https://snips.ai/.

PyTorch implementation of Densely Connected Time Delay Neural Network

p2p speech encrypting device with analog audio interface suitable for GSM phones

Mobile application for exploring fitness data using both speech and touch interaction.

CVPR 2022: Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?

Сценарии для системы домашней автоматизации Majordomo

Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!

Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.

Wav2Vec for speech recognition, classification, and audio classification

https://dodiku.github.io/audio_noise_clustering/results/ ==> An experiment with a variety of clustering (and clustering-like) techniques to reduce noise on an audio speech recording.

a simple php implementation of a Nabaztag server

A proof-of-concept app using KeenASR SDK on Android. WE ARE HIRING: https://keenresearch.com/careers.html

Converts an audio file to LINEAR16 Google-speech compatible file.

A repo listing known open source voice tools, ordered by where they sit in the voice stack

Efficient voice activity detection algorithm using long-term speech information

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

Joint Dictionary Learning-based Non-Negative Matrix Factorization for Voice Conversion (TBME 2016)

Use ctc to do chinese speech recognition by keras / 通过keras和ctc实现中文语音识别

A MXNet implementation of Baidu's DeepSpeech architecture

how to use the Google Cloud Speech API to transcribe audio/video files.

🙊 A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

Time-domain Audio Separation Network (IN PYTORCH)

Emailing System for visually impaired persons

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)

CVC: Contrastive Learning for Non-parallel Voice Conversion (INTERSPEECH 2021, in PyTorch)

Audio or speech signal processing guide.

alternative form of inputs for in-VR interaction with the content of a scene

Auto Segmentation Criterion (ASG) implemented in pytorch

Simple sentence mixing tool (work in progress)

Learn how to build a simple text-to-speech voice app for the web using the Web Speech API.

TensorFlow implementation of "Attentive Modality Hopping for Speech Emotion Recognition," ICASSP-20

Implementation of MelNet in PyTorch to generate high-fidelity audio samples

Official implementation of Meta-StyleSpeech and StyleSpeech

Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching

Pitch shifter using WSOLA and resampling implemented by Python3

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

Feature extraction of speech signal is the initial stage of any speech recognition system.

A list of publicly available room impulse response datasets and scripts to download them.

The Hidden Markov Model Toolkit (HTK) from University of Cambridge, with fixed issues.

End-to-end spoken language identification out of the box.

Transformer implementation speciaized in speech recognition tasks using Pytorch.

Jarvis Home Automation

Massively multilingual pronunciation mining

Scripts for LIUM SpkDiarization tools

KAREN: Unifying Hatespeech Detection and Benchmarking