Finetuning for ASR and the dataset preparation

[Gxhappiness]

Hi, I want to finetune the ASR on the custom dataset, so 2 issues have arisen： 1.How can I do the finetuning for ASR? Is it possible to make modifications only on finetune.py? How can I make modifications? 2.What format should I prepare the dataset? What is the content of manifest.json? Can anyone provide the specific content of the manifest.json?

[adnankarim]

{"source": {"id": 1806, "lang": "eng", "text": "", "audio_local_path": "path to .wav", "waveform": null, "sampling_rate": 16000, "units": null}, "target": {"id": 1806, "lang": "urd", "text": "", "audio_local_path": "path to 491841998166793263.wav", "waveform": null, "sampling_rate": 16000, "units": null}}

write

[Gxhappiness]

{"source": {"id": 1806, "lang": "eng", "text": "", "audio_local_path": "path to .wav", "waveform": null, "sampling_rate": 16000, "units": null}, "target": {"id": 1806, "lang": "urd", "text": "", "audio_local_path": "path to 491841998166793263.wav", "waveform": null, "sampling_rate": 16000, "units": null}}

write

thx

[MuhammadWaqarSahi]

can you share notebook which are helpful for the ASR custom finetuning