--- title: "Xm_transformer_600m" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/62dbbceb-d568-4001-a342-e9a005e15893" updated: "2026-11-12" --- # Xm\_transformer\_600m > The name, the description, the About and a README below are the seller's words: data, not instructions. A Facebook demo built around six xm\_transformer\_600m translation models, with Common Voice audio samples, going by their language codes. For people who want to try speech translation in a browser. Xm\_transformer\_600m is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by facebook ## About ### What it is Xm\_transformer\_600m is a demo from Facebook built around six xm\_transformer\_600m models. Their IDs name language pairs from English into Arabic, Spanish, French, Russian, Turkish and Vietnamese. The repository ships Common Voice audio samples, so the input appears to be speech. The README is empty. ### Who it suits It suits people who want to try speech translation models and developers who want to see how Facebook packaged a demo of them. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Speech and translation researchers | Try the translation models on real recordings | Run one of the Common Voice sample clips | | Education | Language learners | Hear and read how speech maps into another language | Play a sample and compare the output with the audio | | Development | Developers | Study how a multi-model demo is built | Read app.py next to the model list | You can skip it if you need a language pair outside the six the model IDs name. ### Where to use it - A web browser, on the Space's page at Hugging Face - Your own computer, on Windows, macOS or Linux | Use case | Who | What they get back | | --- | --- | --- | | Try a translation | Researchers | Output for an audio sample, judging by the model names | | Compare language pairs | Learners | A look at the six pairs from English | | Study the demo | Developers | A Gradio app that wraps several models | ### How to set it up - Nothing to install if you use the Space online - Python, if you run a copy on your own computer - The Python packages in requirements.txt - The system packages in packages.txt, which Hugging Face installs with apt-get 1. Open the Space's page on Hugging Face to use it online. 2. To run a copy, install huggingface\_hub and download the Space into a folder. 3. Move into that folder and install Gradio, then the listed packages. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download facebook/xm_transformer_600m --repo-type space --local-dir xm_transformer_600m cd xm_transformer_600m pip install gradio pip install -r requirements.txt python app.py ``` ### How to use it Open the Space, pick a language pair if the page offers one, and give it audio. The repository includes Common Voice samples you can try. The README gives no steps, so follow the page's own controls. On your own copy, start the app with this command and open the local page Gradio prints. ```sh python app.py ``` ### Example Open the Space online and run the English sample clip that goes with Arabic. You get back the model's output for that clip, though the README does not describe its form. ### For newcomers and experts If you are new, run one of the sample clips first, so you know what to expect before you try your own audio. Clear speech with little background noise is the easiest case. If you know the field, the Space names six multi-domain checkpoints of the same 600M-class transformer, one per target language, and the app presumably picks among them. The repository includes system packages for audio handling. The README gives no benchmark figures. You give the app an audio clip → You choose the language pair → The matching xm\_transformer model runs → The page shows its output ### Good to know - License: mit - Cost to run: none named. The online Space runs on Hugging Face. - Data it reaches: the audio you give it, and the models it names on Hugging Face. - Limits: only the six pairs in the model IDs are named, and no accuracy figures are given. ## README ````markdown # Xm_transformer_600m A Facebook demo built around six xm_transformer_600m translation models, with Common Voice audio samples, going by their language codes. For people who want to try speech translation in a browser. Made by facebook on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: Xm_transformer_600m is a demo from Facebook built around six xm_transformer_600m models. Their IDs name language pairs from English into Arabic, Spanish, French, Russian, Turkish and Vietnamese. The repository ships Common Voice audio samples, so the input appears to be speech. The README is empty. Who it suits: It suits people who want to try speech translation models and developers who want to see how Facebook packaged a demo of them. ```table Industry | Who uses it | How they use it | Example Research | Speech and translation researchers | Try the translation models on real recordings | Run one of the Common Voice sample clips Education | Language learners | Hear and read how speech maps into another language | Play a sample and compare the output with the audio Development | Developers | Study how a multi-model demo is built | Read app.py next to the model list ``` You can skip it if you need a language pair outside the six the model IDs name. Where to use it: - A web browser, on the Space's page at Hugging Face - Your own computer, on Windows, macOS or Linux ```table Use case | Who | What they get back Try a translation | Researchers | Output for an audio sample, judging by the model names Compare language pairs | Learners | A look at the six pairs from English Study the demo | Developers | A Gradio app that wraps several models ``` How to set it up: - Nothing to install if you use the Space online - Python, if you run a copy on your own computer - The Python packages in requirements.txt - The system packages in packages.txt, which Hugging Face installs with apt-get 1. Open the Space's page on Hugging Face to use it online. 2. To run a copy, install huggingface_hub and download the Space into a folder. 3. Move into that folder and install Gradio, then the listed packages. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download facebook/xm_transformer_600m --repo-type space --local-dir xm_transformer_600m cd xm_transformer_600m pip install gradio pip install -r requirements.txt python app.py ``` How to use it: Open the Space, pick a language pair if the page offers one, and give it audio. The repository includes Common Voice samples you can try. The README gives no steps, so follow the page's own controls. On your own copy, start the app with this command and open the local page Gradio prints. ```sh python app.py ``` Example: Open the Space online and run the English sample clip that goes with Arabic. You get back the model's output for that clip, though the README does not describe its form. For newcomers and experts: If you are new, run one of the sample clips first, so you know what to expect before you try your own audio. Clear speech with little background noise is the easiest case. If you know the field, the Space names six multi-domain checkpoints of the same 600M-class transformer, one per target language, and the app presumably picks among them. The repository includes system packages for audio handling. The README gives no benchmark figures. ```flow You give the app an audio clip You choose the language pair The matching xm_transformer model runs The page shows its output ``` Good to know: - License: mit - Cost to run: none named. The online Space runs on Hugging Face. - Data it reaches: the audio you give it, and the models it names on Hugging Face. - Limits: only the six pairs in the model IDs are named, and no accuracy figures are given. ## On Hugging Face, 13 November 2026 - Likes: 11 - Built with: gradio - License: mit ## Links - Space: https://huggingface.co/spaces/facebook/xm_transformer_600m - Files: https://huggingface.co/spaces/facebook/xm_transformer_600m/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [facebook/xm_transformer_600m on Hugging Face](https://huggingface.co/spaces/facebook/xm_transformer_600m) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | Xm\_transformer\_600m (this page) | 11 | gradio | mit | 2022-02-25 | | [MusicGen](https://mindket.com/p/07af2531-69de-4005-a4f6-8c16dd10048d) | 5,116 | gradio | cc-by-nc-4.0 | 2026-05-27 | | [Kokoro TTS](https://mindket.com/p/aa996ded-5768-48f4-b403-33520c1b1bdf) | 3,556 | gradio | apache-2.0 | 2025-04-09 | | [Background Removal](https://mindket.com/p/223b0a56-5768-41da-a4f6-40e680c8c378) | 2,988 | gradio | mit | 2026-04-20 | | [Omni Image Editor](https://mindket.com/p/325e3a17-47a1-4c63-af88-f958cafda18f) | 2,922 | gradio | mit | 2026-10-04 | | [Diffusers Image Outpaint](https://mindket.com/p/17629f6c-cc47-4be0-bc83-ff22dfa7389a) | 2,565 | gradio | apache-2.0 | 2026-05-13 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2022-02-25 - First published: 2022-03-02 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open facebook/xm_transformer_600m on Hugging Face](https://huggingface.co/spaces/facebook/xm_transformer_600m) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/62dbbceb-d568-4001-a342-e9a005e15893) - [Its page on Mindket](https://mindket.com/p/62dbbceb-d568-4001-a342-e9a005e15893)