# Large model fine-tuning

The first fine-tuned version of Qwen2.5 32B, designed to address its excessive censorship issues and support multilingual interactions.

InternViT-6B-448px-V1-5 is a vision foundation model fine-tuned based on InternViT-6B-448px-V1-2, featuring strong robustness, OCR capabilities, and high-resolution processing.

InternViT-6B-448px-V1-2 is a foundational vision model with a feature backbone, comprising 55.4 million parameters, supporting image processing at 448x448 pixels.

Frisian speech recognition model based on the wav2vec2-large-xls-r-1b architecture, specifically optimized for elderly users

French speech recognition model fine-tuned from openai/whisper-large-v2, trained on over 2200 hours of French audio data

This model is a speech recognition model fine-tuned on the Common Voice Turkish dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate of 30.36% on the evaluation set.

Korean speech recognition model fine-tuned on the Ksponspeech dataset, optimized based on Wav2vec2-large-xlsr-53

This model is a fine-tuned Arabic speech recognition model based on facebook/wav2vec2-xls-r-300m on the Common Voice dataset, achieving a word error rate of 0.5078 on the evaluation set.

This model is a Turkish speech recognition model fine-tuned on the common_voice dataset based on facebook/wav2vec2-xls-r-300m

This model is a fine-tuned version based on facebook/wav2vec2-xls-r-300m, specifically optimized for Urdu speech recognition tasks.

This is a Turkish speech recognition model fine-tuned on the Common Voice dataset based on Facebook's wav2vec2-xls-r-300m model.

A Dutch speech recognition model fine-tuned on Dutch spoken language corpus using CTC loss function, based on the facebook/wav2vec2-large-xlsr-53 large model

A Dutch Wav2Vec2 model built by continuous pre-training and fine-tuning the original English model on the Dutch speech corpus CGN.

This model is a speech recognition model fine-tuned on the Common Voice Turkish dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate of 0.3907 on the evaluation set.

A speech recognition model fine-tuned on the Common Voice Turkish dataset based on facebook/wav2vec2-xls-r-300m

A fine-tuned version of Facebook's wav2vec2-xls-r-1b model for Finnish automatic speech recognition tasks, trained on 275.6 hours of annotated Finnish speech data

Italian news summarization model fine-tuned on Fanpage and Il Post corpora based on the IT5 large model

Portuguese automatic speech recognition model fine-tuned on the CORAA dataset based on facebook/wav2vec2-xls-r-1b

Urdu speech recognition model based on the wav2vec2-large-xls-r-300m architecture, fine-tuned on the Common Voice dataset

This model is an automatic speech recognition model fine-tuned on the Common Voice Swedish dataset based on facebook/wav2vec2-xls-r-1b, supporting Swedish speech-to-text tasks.

A Telugu speech recognition model fine-tuned on the OPENSLR_SLR66-NA dataset based on facebook/wav2vec2-xls-r-1b, supporting automatic speech recognition tasks.

This is an automatic speech recognition (ASR) model fine-tuned for Japanese speech recognition tasks based on the facebook/wav2vec2-large-xlsr-53 model.

This is a Hindi speech recognition model fine-tuned on Hindi datasets based on the facebook/wav2vec2-xls-r-300m model, supporting Hindi speech-to-text tasks.

An automatic speech recognition model fine-tuned on Hebrew datasets based on facebook/wav2vec2-xls-r-1b

This model is an automatic speech recognition (ASR) model fine-tuned on the COMMON_VOICE-TR Turkish dataset based on facebook/wav2vec2-xls-r-2b

This is a Portuguese automatic speech recognition model based on the XLS-R 1B architecture, fine-tuned on multiple Portuguese speech datasets.

This is a speech recognition model fine-tuned on the Common Voice Spanish dataset based on the facebook/wav2vec2-xls-r-300m model, achieving a word error rate of 21.17% on the evaluation set.

This model is an automatic speech recognition model fine-tuned on the Romanian Common Voice 7.0 dataset based on facebook/wav2vec2-xls-r-1b.

This is an automatic speech recognition (ASR) model fine-tuned on the Hindi Common Voice 8 dataset based on the facebook/wav2vec2-xls-r-300m model.

This model is an automatic speech recognition (ASR) model fine-tuned on the Kazakh (KK) dataset based on facebook/wav2vec2-xls-r-300m, with language model (LM) enhancement support

This is an automatic speech recognition (ASR) model fine-tuned on the Hindi Common Voice 7.0 dataset, based on Facebook's wav2vec2-xls-r-300m model.

This model is an automatic speech recognition (ASR) model fine-tuned on the Mozilla Common Voice 8.0 Arabic dataset based on facebook/wav2vec2-xls-r-1b, supporting Arabic speech-to-text tasks.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on a general speech dataset for speech recognition tasks.

An automatic speech recognition model fine-tuned on the Nynorsk (NN) speech dataset based on facebook/wav2vec2-xls-r-1b