# Large parameter model

A Catalan-Spanish bilingual automatic speech recognition model based on the NVIDIA Spanish model

IndicConformer is a Conformer-based automatic speech recognition model with hybrid CTC-RNNT architecture, specifically optimized for Nepali language

IndicConformer is a Conformer-based automatic speech recognition (ASR) model with a hybrid CTC-RNNT architecture, supporting Hindi speech transcription.

PhoGPT is an open-source series of 4-billion-parameter Vietnamese language generation models, including the base pre-trained model PhoGPT-4B and its conversational variant PhoGPT-4B-Chat.

PhoGPT is currently the most advanced 4-billion-parameter Vietnamese language generation model series, including the base pre-trained monolingual model PhoGPT-4B and its conversational variant PhoGPT-4B-Chat.

Multilingual translation model fine-tuned on the WMT16 dataset, supporting Russian to English translation tasks

CodeFuse-13B is a 13-billion-parameter code generation model trained on the GPT-NeoX framework, supporting over 40 programming languages and capable of processing code sequences up to 4096 characters long.

A version fine-tuned on Korean datasets based on the Llama2 70B model, focusing on Korean and English text generation tasks

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

Palmyra-Med-20b is a large language model in the medical field with 20 billion parameters. It is fine-tuned on a medical dataset based on Palmyra-Large and is good at medical dialogue and Q&A tasks.

replit-code-v1-3b is a 2.7B parameter causal language model focused on code completion, developed by Replit, Inc.

A self-supervised feature representation model based on ConvNeXt-V2, pre-trained using the Fully Convolutional Masked Autoencoder (FCMAE) framework, suitable for image classification and feature extraction tasks.

This is a large Conformer-Transducer model for transcribing Mandarin speech, with approximately 120 million parameters, trained on the AISHELL-2 dataset.

CodeParrot is a Python code generation model based on the GPT-2 architecture (1.5 billion parameters), focusing on automatic Python code generation.

This model is a Korean automatic speech recognition model fine-tuned on the KRESNIK/ZEROTH_KOREAN - CLEAN dataset based on facebook/wav2vec2-xls-r-1b

Facebook's Wav2Vec2 XLS-R model fine-tuned for speech translation tasks, supporting translation from English to 15 target languages.

An automatic speech recognition model fine-tuned on the Common Voice Indonesian dataset based on facebook/wav2vec2-xls-r-1b

ruT5-large is a Russian text-to-text generation model developed by the SberDevices team, based on the T5 architecture with 737 million parameters.

Facebook's Wav2Vec2 XLS-R model, fine-tuned for speech translation tasks in 15 languages, capable of translating spoken English into multiple written languages.

A Russian automatic speech recognition model fine-tuned on the Common Voice dataset based on facebook/wav2vec2-xls-r-1b