Fabio
c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
57 lines
1.8 KiB
JSON
57 lines
1.8 KiB
JSON
{
|
|
"id": "speech_redub",
|
|
"description": "Transcribe long speech in chunks and regenerate it in a target reference voice using the same language.",
|
|
"inputs": {
|
|
"source_audio": "${workflow_dir}/../resources/speech.wav",
|
|
"target_voice": "${workflow_dir}/../resources/sample.wav",
|
|
"language": "English",
|
|
"target_voice_text": "Some call me nature. Others call me Mother Nature. I've been here for over 4.5 billion years. Twenty-two thousand five hundred times longer than you."
|
|
},
|
|
"final_audio": "${redub.audio_path}",
|
|
"steps": [
|
|
{
|
|
"id": "prepare_source",
|
|
"type": "convert_audio",
|
|
"input": "${source_audio}",
|
|
"output": "${out_dir}/source/speech_16k.wav",
|
|
"sample_rate": 16000,
|
|
"channels": 1
|
|
},
|
|
{
|
|
"id": "transcribe",
|
|
"type": "chunked_model",
|
|
"family": "qwen3_asr",
|
|
"model": "../../models/Qwen3-ASR-0.6B",
|
|
"task": "asr",
|
|
"mode": "offline",
|
|
"chunk_seconds": 30,
|
|
"overlap_seconds": 0,
|
|
"text_out": "${out_dir}/transcribe/transcript.txt",
|
|
"request": {
|
|
"id": "transcribe",
|
|
"audio": "${prepare_source.audio_path}",
|
|
"language": "${language}",
|
|
"text": "Transcribe the speech exactly."
|
|
}
|
|
},
|
|
{
|
|
"id": "redub",
|
|
"type": "model",
|
|
"family": "qwen3_tts",
|
|
"model": "../../models/Qwen3-TTS-12Hz-1.7B-Base",
|
|
"task": "tts",
|
|
"mode": "offline",
|
|
"out_dir": "${out_dir}/redub",
|
|
"audio_out": "${out_dir}/speech_redub.wav",
|
|
"request": {
|
|
"id": "redub",
|
|
"text": "${transcribe.text}",
|
|
"language": "${language}",
|
|
"voice_ref": "${target_voice}",
|
|
"reference_text": "${target_voice_text}",
|
|
"seed": 1234,
|
|
"do_sample": false
|
|
}
|
|
}
|
|
]
|
|
}
|