SpeechRecognition/test/real/test_config.yaml

68 lines
2.0 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ============================================
# 端到端真实测试配置文件
# ============================================
# 说明:此配置文件用于端到端真实测试,可根据需要修改测试文件路径
# ============================================
# 测试文件配置
test_files:
# 主测试视频文件(用于完整流程测试)
primary_video: "input/VID_20251104_085655_024.AVI"
# 备用测试文件(当主文件不可用时)
backup_videos:
- "input/VID_20251104_090655_025.AVI"
# 音频文件(用于单独测试 ASR
audio_files:
- "input/VID_20251031_132320_019_mono.wav"
- "input/VID_20251031_132320_019_mono_speak_only.wav"
# 测试超时配置(秒)
timeouts:
# ASR 识别超时(长音频可能需要更长时间)
asr_recognize: 600
# 视频转码超时
transcode: 300
# 单个测试用例超时
test_case: 900
# 性能测试阈值
performance:
# 最大可接受的 ASR 处理时间(秒)
max_asr_time: 200
# 最大可接受的转码时间(秒)
max_transcode_time: 600
# 最小处理速度(秒/秒,即 realtime factor
min_processing_speed: 0.5
# 测试环境配置
environment:
# 是否跳过 GPU 测试(如果无 GPU 则设为 true
skip_gpu_tests: false
# 是否跳过大文件测试(>100MB
skip_large_files: false
# 最大测试文件大小MB
# 注意:此限制仅用于测试验证,实际项目无文件大小限制
max_file_size_mb: 1024 # 1GB适应大视频文件
# 测试数据验证
validation:
# ASR 结果最小置信度
min_asr_confidence: 0.6
# 说话人分离最小说话人数
min_speakers: 1
# 说话人分离最大说话人数
max_speakers: 10
# 时间戳精度(秒)
timestamp_precision: 0.1
# 输出配置
output:
# 是否保留测试生成的临时文件(调试用)
keep_temp_files: false
# 是否保存详细日志
verbose_logging: true
# 测试结果输出目录
result_dir: "test_output"