MIDI Dataset variations based on IMSLP (imslp.org)
🏗️ Building on HF
Tim Sockel
TiMauzi
AI & ML interests
NLP, Music/Audio
Recent Activity
updated a model 8 days ago
TiMauzi/wav2vec2-large-xls-r-300m-dsb-with-hsb-pretraining-2 updated a model 8 days ago
TiMauzi/wav2vec2-large-xls-r-300m-dsb-base-2 updated a collection 9 days ago
Sorbian wav2vec2 ModelsOrganizations
None yet
Fine-tuned wav2vec2 models for Upper and Lower Sorbian
-
Sorbian Speech Recognition
🦞Transcribes Sorbian audio recording or audio files
-
TiMauzi/wav2vec2-large-xls-r-300m-dsb-with-hsb-pretraining-2
Automatic Speech Recognition • 0.3B • Updated • 22 -
TiMauzi/wav2vec2-large-xls-r-300m-dsb-base-2
Automatic Speech Recognition • 0.3B • Updated • 20 -
TiMauzi/wav2vec2-large-xls-r-300m-hsb-2
Automatic Speech Recognition • 0.3B • Updated • 15
MIDI Dataset variations based on IMSLP (imslp.org)
Fine-tuned wav2vec2 models for Upper and Lower Sorbian
-
Sorbian Speech Recognition
🦞Transcribes Sorbian audio recording or audio files
-
TiMauzi/wav2vec2-large-xls-r-300m-dsb-with-hsb-pretraining-2
Automatic Speech Recognition • 0.3B • Updated • 22 -
TiMauzi/wav2vec2-large-xls-r-300m-dsb-base-2
Automatic Speech Recognition • 0.3B • Updated • 20 -
TiMauzi/wav2vec2-large-xls-r-300m-hsb-2
Automatic Speech Recognition • 0.3B • Updated • 15
Models which predict musical eras based on MIDI files.