This is an implementation of paper "End-to-end Speech Translation via Cross-modal Progressive Training" (Interspeech2021)

Limit the use of end-to-end data for Speech Translation (by leveraging Automatic Speech Recognition and Machine Translation data instead) using zero-shot multilingual text translation techniques.

Systems submitted to IWSLT 2022 by the MT-UPC group.

code for paper "Cross-modal Contrastive Learning for Speech Translation" (NAACL 2022)

PyTorch toolkit for streaming speech recognition, speech translation and simultaneous translation based on fairseq.

Code for the paper "Does Joint Training Really Help Cascaded Speech Translation?" (EMNLP 2022)

Code for EMNLP 2022 main conference paper "Information-Transport-based Policy for Simultaneous Translation"

Speech to text and translation client-server using Google cloud

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

Revisiting End-to-End Speech-to-Text Translation From Scratch

Zero -- A neural machine translation system

The project for speech translation

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

Code for ACL 2023 main conference paper "Understanding and Bridging the Modality Gap for Speech Translation".

Code for ACL 2023 main conference paper "Back Translation for Speech-to-text Translation Without Transcripts".

unsupervised spoken utterances scoring

Source code for ACL 2023 paper "End-to-End Simultaneous Speech Translation with Differentiable Segmentation"

A realtime speech transcription and translation application using Whisper OpenAI and free translation API. Interface made using Tkinter. Code written fully in Python.

A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing