{
"dataset_param": {
"dataset_type": "audio",
"basic_parameters": {
"dataset_name_or_path": "mozilla-foundation/common_voice_11_0",
"language": "hi"
},
"preprocess_parameters": {
"processor_name_or_path": "openai/whisper-large-v3",
"language": "Hindi",
"task": "transcribe"
}
},
"dataloader_param": {
"dataloader_mode": "sampler",
"shuffle": true,
"drop_last": false,
"pin_memory": true,
"collate_param": {
"model_name": "whisper",
"processor_name_or_path": "openai/whisper-large-v3",
"language": "Hindi",
"task": "transcribe"
}
}
}