Average Model Cost: $0.0000
Number of Runs: 12,823,668
Models by this creator
bart-large-mnli
bart-large-mnli
bart-large-mnli is a pretrained model that uses the BART architecture for zero-shot classification. It can classify textual data into different categories without any prior training in those categories. This model is particularly useful for tasks like text classification, sentiment analysis, and document classification.
$-/run
4.1M
Huggingface
encodec_24khz
encodec_24khz
The encodec_24khz model is an encoder-decoder model that is trained to extract features from audio signals with a sampling rate of 24 kHz. It is designed to transform the raw audio data into a compact and meaningful representation that can be used for various audio processing tasks. The model is trained on a large dataset of audio signals and can be used in applications such as speech recognition, music analysis, and audio synthesis.
$-/run
1.6M
Huggingface
bart-large
bart-large
BART-large is a large-scale transformer-based language model that can be used for a variety of natural language processing tasks. It is pre-trained on a large corpus of text data and can be fine-tuned for specific downstream tasks such as text generation, summarization, question answering, and machine translation. BART-large uses a bidirectional encoder to understand the context of the input text and a decoder to generate appropriate responses or summaries. It has achieved state-of-the-art performance on various benchmark datasets and is widely used in the research community. The model provides feature extraction capabilities, allowing users to extract useful information from text data for further analysis or modeling purposes.
$-/run
1.5M
Huggingface
bart-large-cnn
bart-large-cnn
bart-large-cnn is a pre-trained language model that specializes in the task of summarization. It is based on the BART (Bidirectional and Auto-Regressive Transformers) architecture and has been trained on a large corpus of news articles. Given a long input document, the model can generate a concise and coherent summary of the most important information contained in the document. This model is particularly well-suited for summarizing news articles and other similar texts.
$-/run
1.1M
Huggingface
vit-mae-base
vit-mae-base
The vit-mae-base model is a type of transformer model that has been trained to perform a variety of tasks. It is based on the Vision Transformer (ViT) architecture, which is designed for image recognition tasks. The model has been fine-tuned on a dataset called Multi-Task Auto-Encoding (MAE), which includes various tasks such as image classification, object detection, and image generation. The vit-mae-base model can be used to perform these tasks in a wide range of applications, including computer vision, robotics, and autonomous systems. It is pre-trained on a large dataset and can be further fine-tuned on task-specific datasets to improve its performance on specific tasks.
$-/run
1.0M
Huggingface
wav2vec2-base-960h
wav2vec2-base-960h
The wav2vec2-base-960h model is an automatic speech recognition (ASR) model. It is trained to convert spoken language into written text. The model uses the wav2vec2 architecture and is fine-tuned on a large amount of multilingual ASR data. It is capable of recognizing and transcribing speech with high accuracy.
$-/run
862.8K
Huggingface
wav2vec2-base-100k-voxpopuli
wav2vec2-base-100k-voxpopuli
The wav2vec2-base-100k-voxpopuli model is an automatic speech recognition (ASR) model. It is based on the wav2vec2 architecture and has been trained on a dataset called VoxPopuli, which contains 100,000 hours of multilingual and multitask supervised data. This model is designed to convert spoken language into written text and can be used in various applications such as transcribing audio recordings, voice assistants, and speech-to-text conversion.
$-/run
733.6K
Huggingface
bart-base
bart-base
bart-base is a pre-trained Transformer-based model that is fine-tuned to perform various natural language processing tasks such as text summarization, translation, and text generation. It utilizes a bidirectional encoder-decoder architecture with a masked language modeling objective during pre-training. This model can be used to generate high-quality abstractive summaries of input text.
$-/run
727.5K
Huggingface
hubert-large-ll60k
hubert-large-ll60k
The hubert-large-ll60k model is a feature extraction model. It has not been provided with a description, but it can be inferred that the model is designed to extract features from audio data. The model is likely trained on a large dataset and can be used to represent audio signals in a lower-dimensional space, making them easier to analyze and process for downstream tasks such as speech recognition or audio classification.
$-/run
621.2K
Huggingface
mms-1b-fl102
mms-1b-fl102
The mms-1b-fl102 model is a fine-tuned Automatic Speech Recognition (ASR) model developed by Facebook's Massive Multilingual Speech project. It is based on the Wav2Vec2 architecture and has been trained on 102 languages. The model consists of 1 billion parameters and can be used to transcribe audio in over 100 languages. It makes use of adapter models to handle the different languages. The model has been trained on the Fleurs dataset and has a license of CC-BY-NC 4.0.
$-/run
564.2K
Huggingface