# Large Model Fine-tuning

Shisa V2 is a bilingual (Japanese/English) general-purpose chat model series trained by Shisa.AI, optimized based on Llama-3.3-70B-Instruct, focusing on improving Japanese task performance while maintaining English capabilities.

A Persian automatic speech recognition model fine-tuned based on Whisper Large v3, trained on the Common Voice 17 dataset, which contains over 250,000 Persian audio samples, significantly improving recognition accuracy and robustness.

This is a sentence-transformers model fine-tuned from ModernBERT-large, designed to map sentences and paragraphs into a 1024-dimensional dense vector space, supporting tasks such as semantic textual similarity and semantic search.

A Japanese automatic speech recognition model fine-tuned on the large-scale Japanese ASR corpus ReazonSpeech v2.0, based on the wav2vec 2.0 Large architecture

BMRetriever is a 7-billion-parameter large language model specifically optimized for biomedical text retrieval tasks, capable of efficiently handling literature retrieval needs in the medical and biological fields.

A large language model fine-tuned based on CodeLlama-34B-Python, achieving 69.5% pass@1 on HumanEval, surpassing GPT-4's performance

TrueTeacher is a factual consistency evaluation model based on the T5-11B architecture, specifically designed to assess factual consistency in summaries.

This model is a speech recognition model fine-tuned on the common_voice_9_0 dataset based on facebook/wav2vec2-xls-r-300m, supporting Portuguese speech-to-text tasks.

This model is a fine-tuned speech recognition model based on jonatasgrosman/wav2vec2-large-xlsr-53-english on the ascend dataset.

LongT5 is a long-sequence text-to-text Transformer model based on T5, employing transient-global attention mechanism, suitable for long-text processing tasks.

This is a Persian speech recognition model fine-tuned on the Common Voice dataset, based on the facebook/wav2vec2-large-xlsr-53 model.

A speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, supporting multilingual speech-to-text tasks

This model is a fine-tuned speech processing model based on wav2vec2-large-xls-r-300m-Urdu, primarily used for Urdu speech recognition tasks.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-2b on the common_voice dataset

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-300m on the common_voice dataset, supporting automatic speech recognition tasks.

This model is a Russian speech recognition model fine-tuned on the Common Voice dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate of 0.468 on the evaluation set.

A speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m, achieving a word error rate (WER) of 1.2628 on the evaluation set.

This is a speech recognition model fine-tuned on Marathi datasets based on the facebook/wav2vec2-xls-r-300m model.

Large-scale biomedical language models based on BERT, ALBERT, and ELECTRA, achieving state-of-the-art results in multiple biomedical tasks

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

This model is a speech recognition model fine-tuned on the DementiaBank dataset based on facebook/wav2vec2-large-960h, primarily used for speech-to-text tasks.

A speech recognition model fine-tuned on a general speech dataset based on facebook/wav2vec2-xls-r-300m

This is an automatic speech recognition (ASR) model fine-tuned on the Japanese Common Voice 8.0 dataset based on facebook/wav2vec2-xls-r-300m, supporting Japanese speech-to-text functionality.

An automatic speech recognition model fine-tuned on the Norwegian written language (Bokmål) speech dataset based on the facebook/wav2vec2-xls-r-1b model

An Urdu automatic speech recognition (ASR) model fine-tuned from Facebook's wav2vec2-xls-r-1b model, trained on the Common Voice 8.0 Urdu dataset