A collection of experimental (WIP) ASR models
Yaroslav Getman
GetmanY1
AI & ML interests
None yet
Organizations
None yet
wav2vec 2.0 models pre-trained with 22.5k hours of Yle Sámi radio broadcasts
-
Sámi ASR
🎤Sámi Automatic Speech Recognition
-
GetmanY1/wav2vec2-base-sami-22k
Automatic Speech Recognition • 95M • Updated • 22 -
GetmanY1/wav2vec2-base-sami-cont-pt-22k
Automatic Speech Recognition • 95M • Updated • 21 -
GetmanY1/wav2vec2-base-sami-22k-finetuned
Automatic Speech Recognition • 94.4M • Updated • 11
wav2vec 2.0 Northern Sámi ASR models fine-tuned on Sámi Parliament speech (https://www.isca-archive.org/interspeech_2024/getman24b_interspeech.pdf)
-
GetmanY1/wav2vec2-xls-r-300m-sami-parl-ext-ft
Automatic Speech Recognition • 0.3B • Updated • 10 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-cont-pt-108h
Automatic Speech Recognition • 0.3B • Updated • 10 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-cont-pt-20h
Automatic Speech Recognition • 0.3B • Updated • 7 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-direct-ft
Automatic Speech Recognition • 0.3B • Updated • 7
wav2vec 2.0 models pre-trained with 158K hours of Finnish speech (https://github.com/aalto-speech/large-scale-monolingual-speech-foundation-models)
-
Finnish ASR
🏆Finnish Automatic Speech Recognition
-
GetmanY1/wav2vec2-base-fi-150k
Automatic Speech Recognition • 95M • Updated • 14 -
GetmanY1/wav2vec2-base-fi-150k-finetuned
Automatic Speech Recognition • 94.4M • Updated • 52 -
GetmanY1/wav2vec2-large-fi-150k
Automatic Speech Recognition • 0.3B • Updated • 47
Collection of colloquial Finnish wav2vec 2.0 models (https://www.isca-archive.org/interspeech_2024/getman24_interspeech.pdf)
-
GetmanY1/wav2vec2-large-fi-lp-cont-pt-1500h
Automatic Speech Recognition • 0.3B • Updated • 225 • 1 -
GetmanY1/wav2vec2-base-fi-lp-cont-pt-1500h
Automatic Speech Recognition • 94.4M • Updated • 19 -
GetmanY1/wav2vec2-base-fi-lp-from-scratch
Automatic Speech Recognition • 95M • Updated • 19 -
GetmanY1/wav2vec2-large-fi-lp-from-scratch
Automatic Speech Recognition • 0.3B • Updated • 23
A collection of experimental (WIP) ASR models
wav2vec 2.0 models pre-trained with 158K hours of Finnish speech (https://github.com/aalto-speech/large-scale-monolingual-speech-foundation-models)
-
Finnish ASR
🏆Finnish Automatic Speech Recognition
-
GetmanY1/wav2vec2-base-fi-150k
Automatic Speech Recognition • 95M • Updated • 14 -
GetmanY1/wav2vec2-base-fi-150k-finetuned
Automatic Speech Recognition • 94.4M • Updated • 52 -
GetmanY1/wav2vec2-large-fi-150k
Automatic Speech Recognition • 0.3B • Updated • 47
wav2vec 2.0 models pre-trained with 22.5k hours of Yle Sámi radio broadcasts
-
Sámi ASR
🎤Sámi Automatic Speech Recognition
-
GetmanY1/wav2vec2-base-sami-22k
Automatic Speech Recognition • 95M • Updated • 22 -
GetmanY1/wav2vec2-base-sami-cont-pt-22k
Automatic Speech Recognition • 95M • Updated • 21 -
GetmanY1/wav2vec2-base-sami-22k-finetuned
Automatic Speech Recognition • 94.4M • Updated • 11
Collection of colloquial Finnish wav2vec 2.0 models (https://www.isca-archive.org/interspeech_2024/getman24_interspeech.pdf)
-
GetmanY1/wav2vec2-large-fi-lp-cont-pt-1500h
Automatic Speech Recognition • 0.3B • Updated • 225 • 1 -
GetmanY1/wav2vec2-base-fi-lp-cont-pt-1500h
Automatic Speech Recognition • 94.4M • Updated • 19 -
GetmanY1/wav2vec2-base-fi-lp-from-scratch
Automatic Speech Recognition • 95M • Updated • 19 -
GetmanY1/wav2vec2-large-fi-lp-from-scratch
Automatic Speech Recognition • 0.3B • Updated • 23
wav2vec 2.0 Northern Sámi ASR models fine-tuned on Sámi Parliament speech (https://www.isca-archive.org/interspeech_2024/getman24b_interspeech.pdf)
-
GetmanY1/wav2vec2-xls-r-300m-sami-parl-ext-ft
Automatic Speech Recognition • 0.3B • Updated • 10 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-cont-pt-108h
Automatic Speech Recognition • 0.3B • Updated • 10 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-cont-pt-20h
Automatic Speech Recognition • 0.3B • Updated • 7 -
GetmanY1/wav2vec2-xls-r-300m-sami-parl-direct-ft
Automatic Speech Recognition • 0.3B • Updated • 7