Post
131
Updated the demo for the new version of the W2V-BERT model for Ukrainian audio recognition.
This is a classic Automatic Speech Recognition or Speech to Text task.
What's new in version three:
β’ more data: 1200 hours
β’ new SentencePiece tokenizer with 512 tokens
β’ feature extraction is done via a Rust extension
Facts:
β’ Training was started from the previous model to speed up the learning process.
β’ Training takes place on two 3090 video cards with 24 GB each.
β’ It is well suited for fine-tuning because the training data is very diverse and mostly noisy.
You can try it here:
Yehor/w2v-bert-uk-v3
Download weights here:
speech-uk/w2v-bert-v3
If you wish to support the speech-uk initiative with a donation, here is the link to Monobank:
https://send.monobank.ua/jar/3Saxixsdua
This is a classic Automatic Speech Recognition or Speech to Text task.
What's new in version three:
β’ more data: 1200 hours
β’ new SentencePiece tokenizer with 512 tokens
β’ feature extraction is done via a Rust extension
Facts:
β’ Training was started from the previous model to speed up the learning process.
β’ Training takes place on two 3090 video cards with 24 GB each.
β’ It is well suited for fine-tuning because the training data is very diverse and mostly noisy.
You can try it here:
Yehor/w2v-bert-uk-v3
Download weights here:
speech-uk/w2v-bert-v3
If you wish to support the speech-uk initiative with a donation, here is the link to Monobank:
https://send.monobank.ua/jar/3Saxixsdua
