seamlessm4t 开源项目推荐（19 个）

Dartvauder /NeuroSandboxWebUI

(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 languages

fabio-sim /Fast-SeamlessM4T-ONNX

ONNX-compatible Fast SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

ashleykleynhans /tts-webui-docker

用于TTS生成的Docker镜像一体化

Abhi-vish /SeamlessM4t-Translator

SeamlessM4t-Translator: Utilizing the powerful Seamless M4t Facebook model in the backend, this project facilitates seamless translation functionalities including S2ST, S2TT, T2ST, and T2TT queries.

Mr-vero /AutoTranslate

A JavaScript module for seamless website auto-translation. Integrates with SeamlessM4T. Utilizes IndexedDB for efficient caching, ensuring fast and reliable translations without complex setups.

johnsutor /llama-jarvis

Turn any LLM into Jarvis

gusanmaz /echosight

EchoSight is a tool that helps visually impaired individuals by audibly describing images taken with a Raspberry Pi Camera or inputted via image path or URL across different operating systems.

Edmon02 /armenian-video-dubbing

Open-source Armenian video dubbing pipeline with ASR, translation, voice cloning, lip-sync, and emotion-aware TTS

axs03 /SeamlessM4Tv2-API

Docker containerized deployable API endpoints for the SeamlessM4Tv2 model generating text-to-speech and speech-to-speech translation audio files.

imane0x /EcoQ

A GenAI-powered mobile app dedicated to fostering environmental awareness and facilitating community-driven initiatives.

Shuyib /zindi_mcv_swahilli

How I used Seamless m4t large to get to the top 5 of the mozilla common voice competition hosted on Zindi

XOREngine /Marvin4000

Real-time audio translation using Whisper + SeamlessM4T / NLLB-200

sanjayy0612 /Nadantara

Nadantara is an experimental open-source research project investigating English-to-Hindi speech translation through knowledge distillation. It explores whether a compact, lightweight speech translation student model can learn effectively by mimicking larger teacher pipelines.

lexust1 /av2txtsum

Automatic speech recognition (ASR)

anushk4 /Speech-Speech-Translation

Translation from one language to another without speech intermediate

mbwika /Tafsiri-S2ST

Tafsiri is an AI-powered speech-to-speech translation app that uses seamlessM4T and Edge TTS models. It is build using NodeJS, PostgreSQL, FastAPI, React (+ Vite), Nginx, and Tailwind CSS

kerrickchan /seamlessm4t-demo

Just Run As It. Note: after install package, remember restart kernal

umair-hassan2 /COCO-Urdu

Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation

rennerdo30 /speakora

Speech-to-speech translation with Meta's SeamlessM4T v2 — CLI, Vue 3 web dashboard and a browser extension that dubs videos as they play. Expressive voice preservation, GPU acceleration, SQLite job queue.