修复并集成说话者分离功能

修复:
- kb-whisper-diarization/whisper_diarization.py 变量名 bug

集成:
- kb-workflow/SKILL.md 步骤5 添加说话者分离选项
- 自动检测 HF_TOKEN 选择识别模式
- 子技能清单添加 kb-whisper-diarization

文档:
- kb-whisper-diarization/SKILL.md 完善 HF_TOKEN 获取步骤
This commit is contained in:
2026-02-15 23:18:11 +08:00
parent 70736bce2e
commit 3dc8d246d0
3 changed files with 68 additions and 9 deletions
+29 -5
View File
@@ -18,12 +18,36 @@
| `WHISPER_CPP_PATH` | whisper.cpp 安装路径 | `~/whisper.cpp` |
| `HF_TOKEN` | HuggingFace Token | `hf_xxx...` |
### 获取 HuggingFace Token
### 获取 HuggingFace Token(必需)
pyannote.audio 需要从 HuggingFace 下载模型,需要先:
1. 注册 HuggingFace 账号:https://huggingface.co
2. 申请模型访问权限:https://huggingface.co/pyannote/speaker-diarization
3. 创建 Token:https://huggingface.co/settings/tokens
pyannote.audio 需要从 HuggingFace 下载模型,按以下步骤操作:
**步骤 1: 注册/登录 HuggingFace**
- 访问 https://huggingface.co
- 注册或登录账号
**步骤 2: 申请模型访问权限**
需要申请以下两个模型的访问权限(点击页面上的 "Access repository" 按钮):
- https://huggingface.co/pyannote/speaker-diarization
- https://huggingface.co/pyannote/segmentation
> ⚠️ 申请后需要等待几分钟到几小时才能获得访问权限
**步骤 3: 创建 Access Token**
1. 访问 https://huggingface.co/settings/tokens
2. 点击 "New token"
3. 选择 "Read" 权限
4. 复制生成的 token(以 `hf_` 开头)
**步骤 4: 设置环境变量**
```bash
# 添加到 ~/.kb_env 文件
echo 'export HF_TOKEN="hf_xxxxxxxxxxxxxxxxxxxxxx"' >> ~/.kb_env
source ~/.kb_env
# 验证
echo $HF_TOKEN
```
## 使用方法
@@ -320,7 +320,7 @@ def main():
result = merge_results(whisper_txt, whisper_srt, diarization, output_dir, basename)
# 清理临时音频
if audio_path != input_path and audio_path.endswith('_audio.wav'):
if audio_path != input_file and audio_path.endswith('_audio.wav'):
try:
os.remove(audio_path)
except Exception: