search

davidmartinrius / speech-dataset-generator

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.
MIT License
166 stars 17 forks source link

TypeError: 'NoneType' object is not iterable #15

Open testujemai opened 5 days ago

testujemai commented 5 days ago

Trying to run it on Kaggle. When pyannote starts, it writes this error.

self.iterate_datasets(datasets, transcription, output_directory, path_to_audio_file, existing_speakers) File "/kaggle/working/speech-dataset-generator/speech_dataset_generator/dataset_generator/dataset_generator.py", line 458, in iterate_datasets for dataset in datasets: TypeError: 'NoneType' object is not iterable

Any ideas please?

davidmartinrius commented 5 days ago

Hi @testujemai , how are you doing?

I don't have enough information to analyze it.

What command and what parameters are you using to run it?

Probably you did not use the parameter --datasets [dataset_name] but I am not sure of this.

testujemai commented 4 days ago

Thanks for fast reply @davidmartinrius.

I'm doing step by step your example notebook. The command I used: !python speech_dataset_generator/main.py --youtube_download https://www.youtube.com/watch?v=ExJZAegsOis --output_directory ./outputs/output_youtube --range_times 5-15 --enhancers deepfilternet resembleai But it is the same error on every other command. I though I don't need to use --datasets parameter if I want ljspeech by default.

Btw, very nice project!