# Multi-dataset fine-tuning

A Hindi speech recognition model fine-tuned based on OpenAI's Whisper-Large-V3, trained on approximately 718 hours of transcribed Hindi speech data

Whisper-V3-Turbo model optimized for Vietnamese automatic speech recognition (ASR) tasks, fine-tuned using multiple Vietnamese datasets

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the IMaSC, Indic TTS Malayalam, and OpenSLR Malayalam training datasets, supporting automatic speech recognition for Malayalam.

A Hindi text-to-speech model fine-tuned from a forked version of Coqui TTS, supporting Hindi and English speech synthesis with Hindi accent

A ViT-based facial expression recognition model fine-tuned on FER2013, MMI, and AffectNet datasets, capable of recognizing seven basic emotions

ViT-based facial expression recognition model, fine-tuned on FER2013, MMI, and AffectNet datasets, supporting seven emotion classifications

Korean text summarization model fine-tuned based on kobart, generating summaries with more short sentences

Matter 7B is a fine-tuned model based on Mistral 7B, designed for text generation tasks, supporting conversational interaction and function calling.

This model is a fine-tuned machine translation model for Kinyarwanda to English, based on Helsinki-NLP/opus-mt-rw-en

Japanese speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input

A Khmer speech recognition model fine-tuned based on OpenAI Whisper-small, trained on OpenSLR, Google FLEURS, and km-speech-corpus datasets

A general-purpose summarizer based on the 3B-parameter google/flan-t5-xl model fine-tuned on multiple summarization datasets, suitable for academic and general scenarios.

Telugu speech recognition model fine-tuned based on OpenAI Whisper-medium, trained on multiple public Telugu ASR datasets

An automatic speech recognition (ASR) model fine-tuned on Japanese speech datasets based on OpenAI Whisper-large-v2

A Danish automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper Medium, trained on Common Voice 11 and FLEURS datasets

Fine-tuned on an enhanced Thai dataset based on openai/whisper-medium for Thai automatic speech recognition

An automatic speech recognition model fine-tuned on Polish datasets based on Whisper Large v2, supporting Polish speech-to-text tasks.

A speech recognition model fine-tuned on Indonesian datasets based on openai/whisper-medium, significantly improving the accuracy of Indonesian recognition.

Portuguese legal domain sentence similarity model based on BERTimbau large model, supporting 1024-dimensional vector representation

A Brazilian Portuguese abstractive text summarization model fine-tuned on PTT5, supporting summarization for various text types including news.

A Q&A model based on DeBERTa-base architecture, jointly fine-tuned on SQuAD1, AQA, and NewsQA datasets

Italian speech recognition model fine-tuned from XLS-R 1B parameter model, supports recognition with language model

A Finnish automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input.

This is a Greek automatic speech recognition model based on the XLSR-Wav2Vec2 architecture, developed by the Hellenic Military Academy and the Technical University of Crete.

A Dutch news summarization model fine-tuned on mbart-large-cc25, supporting CNN/DailyMail and XSum format summarization tasks

Hindi speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input

This is a Russian abstractive summarization model based on the T5 architecture and fine-tuned on multiple datasets, capable of generating concise and accurate text summaries.

A speech recognition model fine-tuned with approximately 270 hours of Vietnamese annotated data, supporting Vietnamese automatic speech recognition tasks

A Finnish automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input

A Malayalam fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input.

A French Q&A model based on CamemBERT, fine-tuned on three French Q&A datasets: PIAF, FQuAD, and SQuAD-FR

This is an automatic speech recognition model fine-tuned on Finnish based on facebook/wav2vec2-large-xlsr-53, but has been marked as an old model, and it is recommended to use newer alternatives.

A French DPR model based on CamemBERT, optimized for French Q&A tasks, fine-tuned on PIAF, FQuAD, and SQuAD-FR datasets

This is a Greek fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53, using the Common Voice and CSS10 Greek datasets.

A Catalan speech recognition model fine-tuned based on the VoxPopuli large model, trained on Common Voice and ParlamentParla datasets

This is a Vietnamese fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53, trained using the Common Voice and Infore_25h datasets.

This is a Greek fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53, trained using the Common Voice and CSS10 datasets.

This is a Catalan speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on multiple Catalan datasets.

A Russian speech recognition model fine-tuned on Facebook's Wav2vec2 Large 100k Voxpopuli model using Common Voice 7.0, M-AILABS datasets, and data augmentation techniques.

A Swedish speech recognition model fine-tuned using NST and Common Voice data, based on Facebook's VoxPopuli-sv base model.