There are 4 repositories under speech-to-speech topic.
A desktop application that uses AI to translate voice between languages in real time, while preserving the speaker's tone and emotion.
Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".
Code for the INTERSPEECH 2023 paper "Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models"
Chatter Box is an android app that is capable of Voice, Text, Image Text Translation, and end-to-end chat translation.
A user-friendly interface for ElevenLabs' API with added audio transcription capability.
Systems submitted to IWSLT 2022 by the MT-UPC group.
Speech-to-Speech translation dataset for German and English (text and speech quadruplets).
This repository contains the code for a speech to speech translation system created from scratch for digits translation from English to Tamil
3-month project on artificial intelligence in teams of 3 with Manon Duboscq and Léa Mariot
A speech-to-speech real-time translation bot for Discord
A flask web-page hosting a speech to speech translation demo
A comparison of E2E and Cascading S2ST systems on the CVSS-C Spanish to English dataset (CommonVoice 4.0)
simple speech to speech chatbot to talk with
Conversational speech chatbot utilizing OpenAI's GPTs and Microsoft Azure's Speech Services
Small Assistant IA like Amazon Echo or Siri (not usable)
Translation from one language to another without speech intermediate
Audio-to-Audio using microsoft/speecht5_vc from HuggingFace