import requests
from pathlib import Path

# 配置
API_URL = "http://localhost:7777/transcriptions"
SEGMENT_FOLDER = Path("segmented_audio/1762410009_21d79e67")
OUTPUT_TXT = "transcription_result.txt"

# 获取所有音频文件
audio_files = sorted(SEGMENT_FOLDER.glob("segment_*.wav"))

print(f"找到 {len(audio_files)} 个音频片段\n")

# 逐个识别
all_texts = []
for audio_file in audio_files:
    print(f"识别: {audio_file.name} ...", end=" ")

    with open(audio_file, "rb") as f:
        files = {"file": (audio_file.name, f, "audio/wav")}
        response = requests.post(API_URL, files=files)

    result = response.json()

    if result["code"] == 200:
        transcriptions = result["data"]["transcription"]
        print(f"✓ ({len(transcriptions)} 段)")

        # 合并该音频片段的所有文本
        segment_text = " ".join([trans["content"] for trans in transcriptions if trans["content"]])
        if segment_text:
            all_texts.append(segment_text)
    else:
        print(f"✗ 失败: {result['message']}")

# 保存到txt文件
with open(OUTPUT_TXT, "w", encoding="utf-8") as f:
    f.write("\n".join(all_texts))

print(f"\n{'=' * 60}")
print(f"✓ 转录完成！")
print(f"  总片段数: {len(audio_files)}")
print(f"  识别段落: {len(all_texts)}")
print(f"  保存文件: {OUTPUT_TXT}")
print(f"{'=' * 60}")

# 预览前3段
if all_texts:
    print("\n前3段预览:")
    for i, text in enumerate(all_texts[:3], 1):
        print(f"{i}. {text}")