Add pretrained weights from Voxpopuli

[mthrok]

VoxPopuli publishes pre-trained models of many different languages under CC BY-NC 4.0 license. We can add them to torchaudio.

non-fine-tuned weights

https://github.com/facebookresearch/voxpopuli#wav2vec-20

• [ ] es - base
• [ ] es - large
• [ ] fr - base
• [ ] fr - large
• [ ] it - base
• [ ] it - large
• [ ] ni - base
• [ ] ni - large
• [ ] sv - base
• [ ] sv - large
• [ ] 23 langs (10k subset) - base
• [ ] 23 langs (10k subset) - large
• [ ] 23 langs (100k subset) - base
• [ ] 23 langs (100k subset) - large

Fine-tuned ASR

https://github.com/facebookresearch/voxpopuli#asr-and-lm

• [ ] cs
• [x] de #1953
• [ ] en #1956
• [x] es #1924
• [ ] et
• [ ] fi
• [x] fr #1919
• [ ] hr
• [ ] hu
• [x] it #1954
• [ ] lt
• [ ] ni
• [ ] pl
• [ ] ro
• [ ] sk
• [ ] sl

[harishsdev]

@mthrok can you please eloborate how to approch to resolve above issues

[harishsdev]

from german how they taken
(VOXPOPULI_ASR_BASE_10K_DE, 'de', "dabei|spielt|auch|eine|sorgfältige|berichterstattung|eine|wichtige|rolle"),