# Low-resource Training

A fine-tuned version of the google/flan-t5-base model for dialogue summarization tasks, using PEFT for parameter-efficient fine-tuning

A speech synthesis model fine-tuned based on microsoft/speecht5_tts, supporting text-to-speech tasks

Text-to-speech model fine-tuned based on microsoft/speecht5_tts

A text classification model fine-tuned based on distilbert-base-uncased, trained for specific tasks.

Shuka v1 is a language model natively supporting Indian language audio understanding, combining a self-developed audio encoder with the Llama3-8B-Instruct decoder, enabling zero-shot multilingual question-answering tasks.

This is a text-to-audio model fine-tuned on a micro punk dataset based on the facebook/musicgen-melody model

A LoRA model fine-tuned based on facebook/musicgen-melody, specializing in generating punk-style music

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset, primarily used for text summarization tasks.

A language model scaled down from Mistral 7B to 248 million parameters, designed for text generation tasks and suitable for downstream task fine-tuning.

A financial news sentiment analysis model fine-tuned based on ProsusAI/finbert, used to predict news sentiment tendencies (buy/neutral/sell)

An audio classification model fine-tuned based on facebook/wav2vec2-base for music genre recognition

A model for gender classification based on text or image data, with unspecified training data.

A 124M-parameter language model based on the GPT-2 architecture, fine-tuned on 2.23B tokens of diverse data with improved text generation capabilities

Gender recognition model fine-tuned on Librispeech-clean-100 dataset, achieving an F1 score of 0.9993 on the test set

This model is a fine-tuned audio classification model based on facebook/wav2vec2-base on the superb dataset, achieving an accuracy of 0.6578 on the evaluation set.

Text summarization generation model fine-tuned based on GPT-2

A Vision Transformer model fine-tuned on an image folder dataset based on Google's ViT base model

This model is an image classification model fine-tuned on the beans dataset based on timm/resnet18.a1_in1k, achieving an accuracy of 69.17%.

This model is a fine-tuned version of facebook/bart-base on the SQuAD dataset, suitable for question-answering tasks.

This is a speech processing test model based on the wav2vec architecture, with unspecified specific uses and training data.

This is an automatically generated test model, primarily for demonstration and experimental purposes.

ALBERT pre-trained model fine-tuned for Traditional Chinese sentiment classification, supporting negative (0) and positive (1) sentiment classification.

A speech recognition model fine-tuned based on facebook/wav2vec2-base, suitable for the TIMIT dataset

This model is an image classification model fine-tuned on an image folder dataset based on facebook/deit-tiny-patch16-224

A speech processing model based on the wav2vec architecture, with unspecified specific uses and training data

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily used for text generation tasks.

A speech recognition model fine-tuned from facebook/wav2vec2-base, trained on toy dataset, supporting audio masking tasks

A fine-tuned speech recognition model based on facebook/wav2vec2-base, suitable for speech-to-text tasks

A fine-tuned version of the Twitter RoBERTa base sentiment model for tweet sentiment analysis

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily used for text generation tasks.

BERT-base-uncased fine-tuned tweet sentiment analysis model, trained for 2 epochs

This is an encoder-decoder image captioning model built on a VIT encoder and GPT2-Hindi decoder, specifically designed for generating Hindi image descriptions.

A fine-tuned version of the bert-base-uncased model, specialized in fill-in-the-blank tasks (masked language modeling)

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily designed for text generation tasks.

A text classification model fine-tuned on the SST2 sentiment analysis dataset based on the DistilBERT base model