chore: updates to build scripts

.devcontainer/devcontainer.json

@@ -15,7 +15,8 @@
 		"vscode": {
 			"extensions": [
 				"mechatroner.rainbow-csv",
-				"eamodio.gitlens"
+				"eamodio.gitlens",
+				"charliermarsh.ruff"
 			]
 		}
 	}

.devcontainer/post-create.sh

@@ -14,4 +14,8 @@ sudo apt-get update && sudo apt-get install -y dotnet-sdk-6.0
 dotnet tool install --global Microsoft.CognitiveServices.Speech.CLI
 
 # Install the Azure Speech SDK for Python
-python -m pip install azure-cognitiveservices-speech
+python -m pip install azure-cognitiveservices-speech ffmpeg-normalize
+
+# Install ffmpeg for GLaDOS post-processing and release generation
+sudo apt-get install -y ffmpeg
+python -m pip install ffmpeg-normalize

generate.sh

@@ -1,50 +1,81 @@
 #!/bin/bash
 
-working_dir=$(pwd)
+# Get the directory of the script
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Change to the script's directory
+cd "${script_dir}" || exit 1
 
 check_dependencies() {
-    if [ ! -f "${working_dir}/voice-gen.py" ]; then
-        echo "Script halt: voice-gen.py not found in '${working_dir}'"
+    if [ ! -f "${script_dir}/voice-gen.py" ]; then
+        echo "Script halt: voice-gen.py not found in '${script_dir}'"
+        exit 1
+    fi
+}
+
+check_file_exists() {
+    if [ ! -f "$1" ]; then
+        echo "Error: File $1 not found!" >&2
         exit 1
     fi
 }
 
 check_dependencies
+check_file_exists "${script_dir}/voice-gen.py"
+check_file_exists "${script_dir}/voice-gen-glados.py"
+
+# Delete logs from previous pass
+find . -name "*.log" -delete
+
+# Azure TTS voice configurations
+voices=(
+    "./voices/cs-CZ.csv cs-CZ-VlastaNeural cz"
+    "./voices/da_DK.csv da-DK-ChristelNeural da"
+    "./voices/da_DK_scripts.csv da-DK-ChristelNeural da/SCRIPTS"
+    "./voices/de-DE.csv de-DE-KatjaNeural de"
+    "./voices/en-GB.csv en-IE-EmilyNeural en"
+    "./voices/en-GB_scripts.csv en-IE-EmilyNeural en/SCRIPTS"
+    "./voices/en-GB.csv en-GB-LibbyNeural en_gb-libby"
+    "./voices/en-GB_scripts.csv en-GB-LibbyNeural en_gb-libby/SCRIPTS"
+    "./voices/en-GB.csv en-GB-RyanNeural en_gb-ryan"
+    "./voices/en-GB_scripts.csv en-GB-RyanNeural en_gb-ryan/SCRIPTS"
+    "./voices/en-US.csv en-US-GuyNeural en_us-guy"
+    "./voices/en-US_scripts.csv en-US-GuyNeural en_us-guy/SCRIPTS"
+    "./voices/en-US.csv en-US-MichelleNeural en_us-michelle"
+    "./voices/en-US_scripts.csv en-US-MichelleNeural en_us-michelle/SCRIPTS"
+    "./voices/en-US.csv en-US-SaraNeural en_us-sara"
+    "./voices/en-US_scripts.csv en-US-SaraNeural en_us-sara/SCRIPTS"
+    "./voices/es-CL.csv es-CL-CatalinaNeural es_cl-catalina"
+    "./voices/es-ES.csv es-ES-ElviraNeural es"
+    "./voices/fr-FR.csv fr-FR-DeniseNeural fr"
+    "./voices/it-IT.csv it-IT-ElsaNeural it"
+    "./voices/it-IT_scripts.csv it-IT-ElsaNeural it/SCRIPTS"
+    "./voices/ja-JP.csv ja-JP-NanamiNeural jp"
+    "./voices/ja-JP_scripts.csv ja-JP-NanamiNeural jp/SCRIPTS"
+    "./voices/pt-PT.csv pt-BR-FranciscaNeural pt"
+    "./voices/ru-RU.csv ru-RU-SvetlanaNeural ru"
+    "./voices/sv-SE.csv sv-SE-SofieNeural se --pitch 'dn10%' --rate 'dn0.9'"
+    "./voices/sv-SE_scripts.csv sv-SE-SofieNeural se/SCRIPTS --pitch 'dn10%' --rate 'dn0.9'"
+    "./voices/uk-UA.csv uk-UA-OstapNeural ua-ostap"
+    "./voices/uk-UA.csv uk-UA-PolinaNeural ua-polina"
+    "./voices/zh-CN.csv zh-CN-XiaoxiaoNeural cn"
+    "./voices/zh-TW.csv zh-TW-HsiaoChenNeural tw"
+    "./voices/zh-HK.csv zh-HK-HiuGaaiNeural hk --rate 'dn1.2'"
+)
+
+# Loop through the Azure TTS configurations
+for voice in "${voices[@]}"; do
+    # Use eval to handle parameters with spaces (e.g., --pitch and --rate)
+    eval "./voice-gen.py ${voice}" || exit 1
+done
+
+# GLaDOS-specific configurations
+glados_voices=(
+    "./voices/en-GB.csv en_gb-glados"
+    "./voices/en-GB_scripts.csv en_gb-glados/SCRIPTS"
+)
 
-# delete logs from previous pass
-find "$(dirname "$0")" -name "*.log" -delete
-
-./voice-gen.py voices/cs-CZ.csv cs-CZ-VlastaNeural cz || exit 1
-./voice-gen.py voices/da_DK.csv da-DK-ChristelNeural da || exit 1
-./voice-gen.py voices/da_DK_scripts.csv da-DK-ChristelNeural da/SCRIPTS || exit 1
-./voice-gen.py voices/de-DE.csv de-DE-KatjaNeural de || exit 1
-./voice-gen.py voices/en-GB.csv en-IE-EmilyNeural en || exit 1
-./voice-gen.py voices/en-GB_scripts.csv en-IE-EmilyNeural en/SCRIPTS || exit 1
-./voice-gen.py voices/en-GB.csv en-GB-LibbyNeural en_gb-libby || exit 1
-./voice-gen.py voices/en-GB_scripts.csv en-GB-LibbyNeural en_gb-libby/SCRIPTS || exit 1
-./voice-gen.py voices/en-GB.csv en-GB-RyanNeural en_gb-ryan || exit 1
-./voice-gen.py voices/en-GB_scripts.csv en-GB-RyanNeural en_gb-ryan/SCRIPTS || exit 1
-./voice-gen-glados.py voices/en-GB.csv en_gb-glados || exit 1
-./voice-gen-glados.py voices/en-GB_scripts.csv en_gb-glados/SCRIPTS || exit 1
-./voice-gen.py voices/en-US.csv en-US-GuyNeural en_us-guy || exit 1
-./voice-gen.py voices/en-US_scripts.csv en-US-GuyNeural en_us-guy/SCRIPTS || exit 1
-./voice-gen.py voices/en-US.csv en-US-MichelleNeural en_us-michelle || exit 1
-./voice-gen.py voices/en-US_scripts.csv en-US-MichelleNeural en_us-michelle/SCRIPTS || exit 1
-./voice-gen.py voices/en-US.csv en-US-SaraNeural en_us-sara || exit 1
-./voice-gen.py voices/en-US_scripts.csv en-US-SaraNeural en_us-sara/SCRIPTS || exit 1
-./voice-gen.py voices/es-CL.csv es-CL-CatalinaNeural es_cl-catalina || exit 1
-./voice-gen.py voices/es-ES.csv es-ES-ElviraNeural es || exit 1
-./voice-gen.py voices/fr-FR.csv fr-FR-DeniseNeural fr || exit 1
-./voice-gen.py voices/it-IT.csv it-IT-ElsaNeural it || exit 1
-./voice-gen.py voices/it-IT_scripts.csv it-IT-ElsaNeural it/SCRIPTS || exit 1
-./voice-gen.py voices/ja-JP.csv ja-JP-NanamiNeural jp || exit 1
-./voice-gen.py voices/ja-JP_scripts.csv ja-JP-NanamiNeural jp/SCRIPTS || exit 1
-./voice-gen.py voices/pt-PT.csv pt-BR-FranciscaNeural pt || exit 1
-./voice-gen.py voices/ru-RU.csv ru-RU-SvetlanaNeural ru || exit 1
-./voice-gen.py voices/sv-SE.csv sv-SE-SofieNeural se --pitch "dn10%" --rate "dn0.9" || exit 1
-./voice-gen.py voices/sv-SE_scripts.csv sv-SE-SofieNeural se/SCRIPTS --pitch "dn10%" --rate "dn0.9" || exit 1
-./voice-gen.py voices/uk-UA.csv uk-UA-OstapNeural ua-ostap || exit 1
-./voice-gen.py voices/uk-UA.csv uk-UA-PolinaNeural ua-polina || exit 1
-./voice-gen.py voices/zh-CN.csv zh-CN-XiaoxiaoNeural cn || exit 1
-./voice-gen.py voices/zh-TW.csv zh-TW-HsiaoChenNeural tw || exit 1
-./voice-gen.py voices/zh-HK.csv zh-HK-HiuGaaiNeural hk --rate "dn1.2" || exit 1
+# Loop through the GLaDOS configurations
+for glados_voice in "${glados_voices[@]}"; do
+    eval "./voice-gen-glados.py ${glados_voice}" || exit 1
+done

voice-gen-glados.py

@@ -2,17 +2,16 @@
 import argparse
 import csv
 import os
-import re
 import sys
+import tempfile
 import time
-from pathlib import Path
-import urllib.request
 import urllib.parse
-import tempfile
+import urllib.request
+
 
 def init_argparse() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
-        usage="%(prog)s [FILE] [LANGDIR]",
+        usage="%(prog)s [FILE] [LANGDIR] [-s DELAY]",
         description="Generate voice packs from CSV list using https://glados.c-net.org/"
     )
 
@@ -34,9 +33,9 @@ def init_argparse() -> argparse.ArgumentParser:
     parser.add_argument('-s',
                         '--delay',
                         type=int,
-                        help="Sleep time processing each translation",
+                        help="Sleep time (in seconds) between processing each translation",
                         required=False,
-                        default='3'
+                        default=3
                         )
 
     return parser
@@ -51,7 +50,7 @@ def try_fetch_sample(req: urllib.request.Request, outfile_fd):
                     out.write(content)
                 return
             else:
-                raise ValueError(f"Content returned isn't a WAV file")
+                raise ValueError("Content returned isn't a WAV file!")
         raise ValueError(f"Speech synthesis failed with status code: {response.status}")
 
 def fetch_sample(text: str, outfile_fd, delay_time: int):
@@ -76,6 +75,9 @@ def main() -> None:
     parser = init_argparse()
     args = parser.parse_args()
 
+    # Print which script is running and the file being processed
+    print(f"Running {os.path.basename(__file__)} to process file: {args.file}")
+
     csv_file = args.file
     csv_rows = 0
     langdir = args.langdir
@@ -135,7 +137,7 @@ def main() -> None:
 
                 line_count += 1
 
-        print(f'Finished processing {csv_rows} entries from "{csv_file}".')
+        print(f'Finished processing {csv_rows} entries from "{csv_file}" using {os.path.basename(__file__)}.')
 
 
 if __name__ == "__main__":

voice-gen.py

@@ -21,7 +21,7 @@
 
 def init_argparse() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
-        usage="%(prog)s [FILE] [VOICE] [LANGDIR]",
+        usage="%(prog)s [FILE] [VOICE] [LANGDIR] [-l LOCALE] [-p PITCH] [-r RATE] [-s DELAY]",
         description="Generate voice packs from CSV list."
     )
 
@@ -54,22 +54,22 @@ def init_argparse() -> argparse.ArgumentParser:
 
     parser.add_argument('-p',
                         '--pitch',
-                        help="Pitch adjustment",
+                        help="Pitch adjustment (e.g., 'up10%', 'dn5%')",
                         type=str,
                         default="default")
 
     parser.add_argument('-r',
                         '--rate',
-                        help="Rate adjustment",
+                        help="Rate adjustment (e.g., 'up10%', 'dn5%')",
                         type=str,
                         default="default")
 
     parser.add_argument('-s',
                         '--delay',
                         type=int,
-                        help="Sleep time processing each translation",
+                        help="Sleep time (in seconds) between processing each translation",
                         required=False,
-                        default='3'
+                        default=3
                         )
 
     return parser
@@ -79,6 +79,9 @@ def main() -> None:
     parser = init_argparse()
     args = parser.parse_args()
 
+    # Print which script is running and the file being processed
+    print(f"Running {os.path.basename(__file__)} to process file: {args.file}")
+
     csv_file = args.file
     csv_rows = 0
     voice = args.voice
@@ -194,7 +197,7 @@ def main() -> None:
 
                 line_count += 1
 
-        print(f'Finished processing {csv_rows} entries from "{csv_file}".')
+        print(f'Finished processing {csv_rows} entries from "{csv_file}" using {os.path.basename(__file__)}.')
 
 
 if __name__ == "__main__":