Pull all TTS binaries (#70)

.gitattributes

@@ -3,7 +3,4 @@
 *.png binary
 *.gif binary
 *.ttf binary
-
-# Git config
-# git config core.eol lf
-# git config core.autocrlf input
+*.data filter=lfs diff=lfs merge=lfs -text

.github/workflows/publish-docker.yml

@@ -29,7 +29,7 @@ jobs:
           password: ${{ secrets.DOCKER_API_KEY }}
 
       - name: Pull TTS Model
-        run: ./services/web/scripts/pull_tts_model.sh
+        run: python ./services/web/scripts/pull_tts_assets.py
 
       - name: Build and Push API Image
         run: |

.gitignore

@@ -32,3 +32,7 @@ output
 /docs/.vitepress/cache
 *.bak
 /services/web/src/static/vendor/tts-sherpa-onnx
+
+# binary
+*.wasm
+*.data

docker/docker-compose.base.yml

@@ -81,4 +81,4 @@ networks:
 
 volumes:
   ollama-data:
-  elasticsearch-data:
+  elasticsearch-data:

docker/docker-compose.dev.yml

@@ -55,4 +55,4 @@ services:
     healthcheck:
       <<: *default-healthcheck
       test: ["CMD", "curl", "-f", "http://localhost:5000/health"]
-    deploy: *shared-deploy
+    deploy: *shared-deploy

docker/docker-compose.prod.yml

@@ -58,4 +58,4 @@ services:
 
 volumes:
   nginx-proxy-data:
-  nginx-proxy-letsencrypt:
+  nginx-proxy-letsencrypt:

run.sh

@@ -207,7 +207,7 @@ function clean_environment() {
 
 function pull_assets() {
     echo "Pulling additional assets..."
-    ./services/web/scripts/pull_tts_model.sh
+    python ./services/web/scripts/pull_tts_assets.py
 }
 
 function ensure_environment() {

services/web/scripts/pull_tts_assets.py

@@ -0,0 +1,88 @@
+import os
+import shutil
+import sys
+import tempfile
+import time
+import urllib.request
+from pathlib import Path
+
+
+def get_script_dir():
+    return Path(__file__).parent.resolve()
+
+
+def setup_target_dir():
+    target_dir = (
+        get_script_dir().parent / "src" / "static" / "vendor" / "tts-sherpa-onnx"
+    )
+
+    if not target_dir.exists():
+        raise RuntimeError(f"Target directory does not exist: {target_dir}")
+    if not os.access(target_dir, os.W_OK):
+        raise RuntimeError(f"Target directory is not writable: {target_dir}")
+
+    return target_dir
+
+
+def download_file(url, target_file, tmp_file, max_retries=3):
+    for attempt in range(max_retries):
+        try:
+            print(f"Downloading {target_file.name}...")
+            urllib.request.urlretrieve(url, tmp_file)
+
+            if not os.path.exists(tmp_file):
+                raise RuntimeError(f"Download file not found: {tmp_file}")
+            if os.path.getsize(tmp_file) == 0:
+                raise RuntimeError(f"Downloaded file is empty: {tmp_file}")
+
+            shutil.move(tmp_file, target_file)
+            print(f"Download completed successfully to: {target_file}")
+            return True
+
+        except Exception as e:
+            if attempt < max_retries - 1:
+                print(
+                    f"Download failed, retrying (attempt {attempt + 1} of {max_retries})..."
+                )
+                time.sleep(2)
+            else:
+                print(f"Error downloading {url}: {str(e)}", file=sys.stderr)
+                return False
+
+
+def main():
+    files = {
+        "sherpa-onnx-wasm-main-tts.data": "https://huggingface.co/spaces/k2-fsa/web-assembly-tts-sherpa-onnx-en/resolve/main/sherpa-onnx-wasm-main-tts.data",  # noqa: E501
+        "sherpa-onnx-wasm-main.wasm": "https://huggingface.co/spaces/k2-fsa/web-assembly-tts-sherpa-onnx-en/resolve/main/sherpa-onnx-wasm-main.wasm",  # noqa: E501
+        "sherpa-onnx-wasm-main-tts.wasm": "https://huggingface.co/spaces/k2-fsa/web-assembly-tts-sherpa-onnx-en/resolve/main/sherpa-onnx-wasm-main-tts.wasm",  # noqa: E501
+    }
+
+    try:
+        target_dir = setup_target_dir()
+
+        print("Pulling Wasm client side TTS...")
+
+        with tempfile.TemporaryDirectory() as temp_dir:
+            for filename, url in files.items():
+                target_file = target_dir / filename
+
+                if target_file.exists():
+                    print(f"File already exists at: {target_file}")
+                    print("Skipping download")
+                    continue
+
+                tmp_file = Path(temp_dir) / f"{filename}.tmp"
+
+                if not download_file(url, target_file, tmp_file):
+                    return 1
+
+        print("All downloads completed successfully!")
+        return 0
+
+    except Exception as e:
+        print(f"Error: {str(e)}", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

services/web/src/static/vendor/tts-sherpa-onnx/.gitattributes

@@ -1,36 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-*.data filter=lfs diff=lfs merge=lfs -text