Downloads · 30 days
25
2% of all-time downloads
FremyCompany/xls-r-2b-nl-v2_lm-5gram-os
xls-r-2b-nl-v2_lm-5gram-os is a automatic speech recognition model from FremyCompany. Use it when you need speech turned into text. It is set up for transformers.
This model is a version of facebook/wav2vec2-xls-r-2b-22-to-16 fine-tuned mainly on the CGN dataset, as well as the MOZILLA-FOUNDATION/COMMONVOICE80 - NL dataset (see details below), on which a large 5-gram language m…
Downloads · 30 days
25
2% of all-time downloads
All-time downloads
1K
Public
Repo size
25.6 GB
Likes
3
Public
Click a slice to open those files.
.bin16.9 GB · 100%
From the Hugging Face model README
This model is a version of facebook/wav2vec2-xls-r-2b-22-to-16 fine-tuned mainly on the CGN dataset, as well as the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - NL dataset (see details below), on which a large 5-gram language model is added based on the Open Subtitles Dutch corpus. This model achieves the following results on the evaluation set (of Common Voice 8.0):
The model takes 16kHz sound input, and uses a Wav2Vec2ForCTC decoder with 48 letters to output the letter-transcription probabilities per frame.
To improve accuracy, a beam-search decoder based on pyctcdecode is then used; it reranks the most promising alignments based on a 5-gram language model trained on the Open Subtitles Dutch corpus.
This model can be used to transcribe Dutch or Flemish spoken dutch to text (without punctuation).
The model was:
5 epochs (6000 iterations of batch size 32) on the cv8/nl dataset.1 epoch (36000 iterations of batch size 32) on the cgn dataset.5 epochs (6000 iterations of batch size 32) on the cv8/nl dataset.