# Multilingual transfer learning

This model is a Russian automatic speech recognition (ASR) model fine-tuned on the common_voice_17_0 dataset based on facebook/wav2vec2-xls-r-300m, with a word error rate (WER) of 0.195.

An efficient multilingual large model based on spectrum fine-tuning technology, supporting multiple languages such as German and English

A 1.3 billion parameter language model optimized for Ukrainian, deeply fine-tuned based on mGPT-XL(1.3B)

indoSBERT-large is an Indonesian sentence embedding model based on sentence-transformers, which maps sentences and paragraphs into a 256-dimensional vector space, suitable for tasks such as clustering and semantic search.

This model is a speech recognition model fine-tuned on an unknown dataset based on facebook/wav2vec2-large-xlsr-53, supporting recognition of Arabic dialects (Arabizi).

English-Filipino speech recognition model fine-tuned from jonatasgrosman/wav2vec2-large-xlsr-53-english, achieving a WER of 0.5750 on the evaluation set

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the filipino_voice dataset, designed for English and Filipino speech recognition tasks.

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the filipino_voice dataset, designed for English-Filipino speech recognition tasks.

English-Filipino speech recognition model fine-tuned based on jonatasgrosman/wav2vec2-large-xlsr-53-english

Speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, optimized on 10ms audio masked training data

Facebook's 300M parameter speech recognition model, fine-tuned for Urdu, trained on the Common Voice 8.0 Urdu dataset

A Nahuatl (ncj dialect) speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53

This model is an Icelandic POS tagging model based on the XLM-RoBERTa architecture, fine-tuned on the Universal Dependencies dataset v2.8.

A token classification model for Wolof named entity recognition (NER) tasks, fine-tuned on the Wolof portion of the MasakhaNER dataset based on xlm-roberta-base

This model is a speech recognition model fine-tuned on the Common Voice Swedish dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate (WER) of 1.0286 on the evaluation set.

Polish automatic speech recognition model developed by Facebook, based on Wav2Vec2 architecture and XLSR-53 multilingual pretrained model

This model is based on the base variant of XLM-RoBERTa, fine-tuned using Gujarati language and OSCAR monolingual datasets, suitable for Gujarati natural language processing tasks.

This model is fine-tuned on the Swahili portion of the MasakhaNER dataset for named entity recognition tasks in Swahili text.

This model is based on OpenAI's medium-scale GPT-2 model, retrained specifically for Italian vocabulary, making it suitable for Italian text generation tasks.