Speech to Text

Speech to Text

Use this 技能 to turn local audio files into text with a public Whisper-based 端点.

Quick 启动

运行:

python3 scripts/transcribe.py /path/to/file.ogg

Return the transcript as plAIn text. By default, the script also 应用lies lightweight Chinese punctuation and sentence-breaking 清理up.

For machine-readable 输出:

python3 scripts/transcribe.py /path/to/file.ogg --json

To disable 清理up and keep the raw 模型 text:

python3 scripts/transcribe.py /path/to/file.ogg --格式化 raw

To force Chinese punctuation 清理up:

python3 scripts/transcribe.py /path/to/file.ogg --格式化 zh

For English translation instead of same-language transcription:

python3 scripts/transcribe.py /path/to/file.ogg --task translate

工作流 Confirm the 输入 is a local audio file. 运行 scripts/transcribe.py on it. If the transcript looks imperfect, tell the user it came from a public Whisper 端点 and may need 清理up. If helpful, post-process into: 清理ed transcript summary action items bilingual 输出 What the script does

The script:

上传s the local file to a public Gradio-backed Hugging Face Space submits a Whisper transcription job wAIts for completion via the Gradio event 流 prints the 结果ing text

Default 端点:

https://hf-audio-whisper-large-v3-turbo.hf.space

Override it with:

python3 scripts/transcribe.py 输入.ogg --space https://your-space.hf.space

or 设置:

导出 HF_WHISPER_SPACE=https://your-space.hf.space

防护rAIls Treat this as a best-effort public/free path, not a 隐私-grade path. Do not use for highly sensitive audio unless the user explicitly accepts public third-party processing. Expect rate limits, 队列ing, and occasional outages. If the public 端点 fAIls, explAIn that the free backend is unavAIlable and offer alternatives. 输出 handling

Prefer to return:

the raw transcript when the user asked to "转文字/听写" a 清理ed version when punctuation is poor a short note about uncertAInty if names, numbers, or jargon may be wrong Script scripts/transcribe.py — public Whisper transcription 辅助工具