Classla

Rank:

Average Model Cost: $0.0000

Number of Runs: 37,678

Models by this creator

bcms-bertic-ner

bcms-bertic-ner

classla

The bcms-bertic-ner model is a fine-tuned version of the BERTić model for named entity recognition (NER) in Bosnian, Croatian, Montenegrin, and Serbian languages. It has been trained on multiple datasets and achieved an F1 score of 91.38 on dev data. The model recognizes four types of named entities: PER (person), LOC (location), ORG (organization), and MISC (miscellaneous). This model is especially useful for NER tasks in these languages.

Read more

$-/run

32.6K

Huggingface

wav2vec2-xls-r-parlaspeech-hr

wav2vec2-xls-r-parlaspeech-hr

wav2vec2-xls-r-parlaspeech-hr This model for Croatian ASR is based on the facebook/wav2vec2-xls-r-300m model and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament dataset ParlaSpeech-HR v1.0. If you use this model, please cite the following paper: Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus. http://www.lrec-conf.org/proceedings/lrec2022/workshops/ParlaCLARINIII/pdf/2022.parlaclariniii-1.16.pdf Metrics Evaluation is performed on the dev and test portions of the ParlaSpeech-HR v1.0 dataset. There are multiple models available, and in terms of CER and WER, the best-performing model is wav2vec2-large-slavic-parlaspeech-hr-lm. Usage in transformers Training hyperparameters In fine-tuning, the following arguments were used:

Read more

$-/run

74

Huggingface

Similar creators