AskaEth
6ef9e082a6
- 前端: VAD语音检测(@ricky0123/vad-web) + useVoiceInput双模式(流式WS/REST) - Gateway: VoiceStreamManager代理WS流式STT到voice-service - Voice-service: DashScope REST → Realtime WS → Whisper三级引擎 + ffmpeg转码 - 共享模块: pkg/audio(音频转换) + pkg/dashscope(ASR REST客户端) - 清理: 移除旧plugin-manager和pkg/plugins，完成插件→工具合并 - 文档: 完善gateway-api.md和voice-service.md语音API文档 - 工具: scripts/voice/ 语音转换脚本集 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
74 lines
1.9 KiB
Bash
74 lines
1.9 KiB
Bash
#!/bin/bash
|
|
# 批量 WEM → WAV 转换 (使用 vgmstream-cli)
|
|
set -e
|
|
|
|
RAW_DIR="D:/Project/Code/Uni/Cyrene-Voice-Model/data/raw"
|
|
CLEANED_DIR="D:/Project/Code/Uni/Cyrene-Voice-Model/data/cleaned"
|
|
VGMSTREAM="D:/Project/Code/Uni/Cyrene/scripts/voice/tools/vgmstream/vgmstream-cli.exe"
|
|
|
|
if [ ! -f "$VGMSTREAM" ]; then
|
|
echo "错误: 找不到 vgmstream-cli.exe"
|
|
exit 1
|
|
fi
|
|
|
|
echo "=== 批量 WEM → WAV 转换 ==="
|
|
echo ""
|
|
|
|
TOTAL=0
|
|
SUCCESS=0
|
|
FAILED=0
|
|
|
|
while IFS= read -r -d '' wem_file; do
|
|
TOTAL=$((TOTAL + 1))
|
|
|
|
# 输出路径: cleaned/ 目录下保持相同子目录结构，改 .wem 为 .wav
|
|
rel_path="${wem_file#$RAW_DIR/}"
|
|
wav_file="${CLEANED_DIR}/${rel_path%.wem}.wav"
|
|
wav_dir="$(dirname "$wav_file")"
|
|
|
|
mkdir -p "$wav_dir"
|
|
|
|
# 跳过已转换的
|
|
if [ -f "$wav_file" ] && [ "$(stat -c%s "$wav_file" 2>/dev/null || echo 0)" -gt 100 ]; then
|
|
SUCCESS=$((SUCCESS + 1))
|
|
continue
|
|
fi
|
|
|
|
# 转换
|
|
if cmd.exe //c "$VGMSTREAM -o \"$wav_file\" \"$wem_file\"" 2>/dev/null; then
|
|
SUCCESS=$((SUCCESS + 1))
|
|
else
|
|
FAILED=$((FAILED + 1))
|
|
fi
|
|
|
|
# 进度显示
|
|
if [ $((TOTAL % 100)) -eq 0 ]; then
|
|
echo " 进度: $TOTAL 文件 (成功: $SUCCESS, 失败: $FAILED)"
|
|
fi
|
|
done < <(find "$RAW_DIR" -name "*.wem" -print0)
|
|
|
|
echo ""
|
|
echo "=== 转换完成 ==="
|
|
echo "总计: $TOTAL | 成功: $SUCCESS | 失败: $FAILED"
|
|
|
|
# 统计分类
|
|
echo ""
|
|
echo "音频时长分布:"
|
|
find "$CLEANED_DIR" -name "*.wav" | while read wav; do
|
|
dur=$(ffprobe -v quiet -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "$wav" 2>/dev/null || echo "0")
|
|
echo "$dur"
|
|
done | awk '
|
|
{ d = $1 + 0 }
|
|
d < 1 { lt1++ }
|
|
d < 3 { lt3++ }
|
|
d < 10 { lt10++ }
|
|
d < 30 { lt30++ }
|
|
d >= 30 { gt30++ }
|
|
END {
|
|
printf " < 1s: %d\n", lt1
|
|
printf " 1-3s: %d\n", lt3
|
|
printf " 3-10s: %d\n", lt10
|
|
printf " 10-30s: %d\n", lt30
|
|
printf " > 30s: %d\n", gt30
|
|
}'
|