From 5daaf77258962dc39a526e90f7f7ade6b2ec3723 Mon Sep 17 00:00:00 2001
From: Quentin Fuxa <quentin.fuxa@gmail.com>
Date: Thu, 3 Jul 2025 10:14:45 +0200
Subject: [PATCH] add download script for SimulStreaming backend

---
 README.md                                     |  2 +-
 .../download_simulstreaming_backend.py        | 30 +++++++++++++++++++
 .../dual_license_simulstreaming.md            | 25 ++++++++++++++++
 3 files changed, 56 insertions(+), 1 deletion(-)
 create mode 100644 whisperlivekit/download_simulstreaming_backend.py
 create mode 100644 whisperlivekit/simul_whisper/dual_license_simulstreaming.md

diff --git a/README.md b/README.md
index e054d2a..85e7d4f 100644
--- a/README.md
+++ b/README.md
@@ -35,7 +35,7 @@ WhisperLiveKit consists of three main components:
 - **Confidence Validation** – Immediately validate high-confidence tokens for faster inference (WhisperStreaming only)
 - **Buffering Preview** – Displays unvalidated transcription segments (not compatible with SimulStreaming yet)
 - **Punctuation-Based Speaker Splitting [BETA]** - Align speaker changes with natural sentence boundaries for more readable transcripts
-- **SimulStreaming Backend** - Ultra-low latency transcription using state-of-the-art AlignAtt policy. The code is not directly included in the repo : To use, please copy [whisper](https://github.com/ufal/SimulStreaming/tree/main/simul_whisper/whisper) folder into `whisperlivekit/simul_whisper/` . ⚠️ You must comply with the [Polyform license](https://github.com/ufal/SimulStreaming/blob/main/LICENCE.txt)
+- **SimulStreaming Backend** - Ultra-low latency transcription using state-of-the-art AlignAtt policy. The code is not bundled directly in this repository. To retrieve it, please run `python whisperlivekit/download_simulstreaming_backend.py`
 
 
 ## Quick Start
diff --git a/whisperlivekit/download_simulstreaming_backend.py b/whisperlivekit/download_simulstreaming_backend.py
new file mode 100644
index 0000000..1c8b4e9
--- /dev/null
+++ b/whisperlivekit/download_simulstreaming_backend.py
@@ -0,0 +1,30 @@
+import os
+import requests
+
+GITHUB_API_URL = "https://api.github.com/repos/ufal/SimulStreaming/contents/simul_whisper/whisper"
+RAW_BASE_URL = "https://raw.githubusercontent.com/ufal/SimulStreaming/main/simul_whisper/whisper"
+TARGET_DIR = os.path.join("whisperlivekit", "simul_whisper", "whisper")
+
+def download_files_from_github(api_url, local_dir):
+    os.makedirs(local_dir, exist_ok=True)
+    response = requests.get(api_url)
+    response.raise_for_status()
+    items = response.json()
+
+    for item in items:
+        if item['type'] == 'file':
+            download_url = item['download_url']
+            file_name = item['name']
+            print(f"Downloading {file_name} ...")
+            file_response = requests.get(download_url)
+            file_response.raise_for_status()
+            with open(os.path.join(local_dir, file_name), 'wb') as f:
+                f.write(file_response.content)
+        elif item['type'] == 'dir':
+            # Recursive call for subdirectories
+            download_files_from_github(item['url'], os.path.join(local_dir, item['name']))
+
+if __name__ == "__main__":
+    print(f"Downloading files into {TARGET_DIR} ...")
+    download_files_from_github(GITHUB_API_URL, TARGET_DIR)
+    print("✅ Download completed successfully.")
\ No newline at end of file
diff --git a/whisperlivekit/simul_whisper/dual_license_simulstreaming.md b/whisperlivekit/simul_whisper/dual_license_simulstreaming.md
new file mode 100644
index 0000000..ee28dd2
--- /dev/null
+++ b/whisperlivekit/simul_whisper/dual_license_simulstreaming.md
@@ -0,0 +1,25 @@
+📄 SimulStreaming (https://github.com/ufal/SimulStreaming) Licence
+
+SimulStreaming is dual-licensed:
+
+🔹 Non-Commercial Use
+
+You may use SimulStreaming under the **PolyForm Noncommercial License 1.0.0** if you
+obtain the code through the GitHub repository.  This license is **free of charge**
+and comes with **no obligations** for non-commercial users.
+
+🔸 Commercial Use
+
+Understanding who uses SimulStreaming commercially helps us improve and
+prioritize development. Therefore, we want to **require registration** of those who acquire a commercial licence.
+
+We plan to make the commercial licenceses **affordable** to SMEs and individuals. We
+are considering to provide commercial licenses either for free or for symbolic
+one-time fee, and maybe also provide additional support. You can share your preference via the [questionnaire](https://forms.cloud.microsoft/e/7tCxb4gJfB).
+
+You can also leave your contact [there](https://forms.cloud.microsoft/e/7tCxb4gJfB) to be notified when the commercial licenses become
+available.
+
+✉️ Contact
+
+[Dominik Macháček](https://ufal.mff.cuni.cz/dominik-machacek/), machacek@ufal.mff.cuni.cz
\ No newline at end of file