Skip to content

Speech2Speech: Enable Radeon dGPU #446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sreeram-11 merged 5 commits into from
Jun 29, 2026
Merged

Speech2Speech: Enable Radeon dGPU #446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
dba9004
Speech2Speech: Enable Radeon dGPU
sreeram-11 Jun 27, 2026
69fb796
Updating pytorch.md
sreeram-11 Jun 28, 2026
624a2cd
Updating rocm.md
sreeram-11 Jun 28, 2026
5bce47a
Updating to Luca's suggestion
sreeram-11 Jun 29, 2026
bf3598b
Merge branch 'main' into sreeram/radeon-speech2speech
sreeram-11 Jun 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions playbooks/supplemental/speech2speech-translation/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ source s2st-env/bin/activate
<!-- @setup:id=activate-venv command="source s2st-env/bin/activate" -->
<!-- @device:end -->

<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
<!-- @device:halo,stx,krk,rx7900xt,rx9070xt,r9700 -->
**Grant your user access to GPU devices** (log out and back in for this to take effect):

```bash
Expand Down Expand Up @@ -95,7 +95,7 @@ s2st-env\Scripts\activate

<!-- @device:end -->

<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
<!-- @device:halo,stx,krk,rx7900xt,rx9070xt,r9700 -->
On Windows, open a terminal in the directory of your choice and follow the commands to create a venv:

<!-- @test:id=create-venv timeout=60 -->
Expand Down
8 changes: 4 additions & 4 deletions playbooks/supplemental/speech2speech-translation/platform.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,27 +4,27 @@ This document describes the expected platform configurations for running this pl

## Prerequisites

PyTorch with ROCm support will be pre-installed on your AMD Developer Platform. Please refer to the relevant section for your operating system:
PyTorch with ROCm support is pre-installed on the AMD Ryzen™ AI Halo Developer Platform. For all other devices, users must manually install PyTorch with ROCm support. Please refer to the relevant section for your operating system:

### Windows

| Component | Version | Notes |
|---------------|-----------------|-----------------------------------|
| **PyTorch** | 2.8 or newer | Preinstalled, available in PATH |
| **PyTorch** | 2.8 or newer | Pre-installed on the AMD Ryzen™ AI Halo Developer Platform; must be manually installed on all other devices |

### Linux

| Component | Version | Notes |
|---------------|-----------------|-----------------------------------|
| **PyTorch** | 2.8 or newer | Preinstalled, available in PATH |
| **PyTorch** | 2.8 or newer | Pre-installed on the AMD Ryzen™ AI Halo Developer Platform; must be manually installed on all other devices |

## Required Models

The following models are tested and optimized for your platform:

| Model | Parameters | Size | Download Location |
|-------|------------|------|-------------------|
| **facebook/seamless-m4t-v2-large** | 2.3B | ~10GB | Pre-installed on AMD Halo Developer Platform |
| **facebook/seamless-m4t-v2-large** | 2.3B | ~10GB | Pre-installed on the AMD Ryzen™ AI Halo Developer Platform; must be manually installed on all other devices |

Models will be automatically downloaded to the Hugging Face cache directory:
- **Windows**: `C:\Users\<username>\.cache\huggingface\hub\`
Expand Down
72 changes: 60 additions & 12 deletions playbooks/supplemental/speech2speech-translation/playbook.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@
"description": "Build a real-time speech-to-speech translation on your local hardware.",
"time": 30,
"supported_platforms": {
"halo": [
"halo_box": [
"linux",
"windows"
],
"halo_box": [
"halo": [
"linux",
"windows"
],
Expand All @@ -19,12 +19,24 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"tested_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -33,12 +45,24 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"required_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -47,16 +71,28 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"published_platforms": {
"halo": [
"windows",
"linux"
],
"halo_box": [
"windows",
"linux"
"linux",
"windows"
],
"halo": [
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -65,6 +101,18 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"difficulty": "intermediate",
Expand Down
Loading