Patrickvonplaten

Rank:

Average Model Cost: $0.0000

Number of Runs: 98,880

Models by this creator

t5-tiny-random

The model with the ID t5-tiny-random is a language generation model that belongs to the Text-to-Text Transformer (T5) family. However, no specific description or details about the model's capabilities were provided.

$-/run

44.1K

Huggingface

wav2vec2_tiny_random

patrickvonplaten

The wav2vec2_tiny_random model is designed for feature extraction from audio signals. It is a smaller version of the wav2vec2 model that has random initialization. The model extracts useful features from audio data that can be used for downstream tasks like speech recognition or speaker identification.

$-/run

24.2K

Huggingface

longformer-random-tiny

patrickvonplaten

The longformer-random-tiny model is a feature extraction model that can be used for various natural language processing tasks. It is designed to handle long documents and has been trained on random text. The model can extract features from text inputs, which can then be used for tasks such as classification, language modeling, and question answering.

$-/run

11.5K

Huggingface

wavlm-libri-clean-100h-base-plus

patrickvonplaten

The wav2vec 2.0 LibriSpeech 100-hour model is a pre-trained automatic speech recognition (ASR) model that can convert spoken language into written text. This model is trained on the LibriSpeech dataset, which consists of 100 hours of clean speech data. The model can be used for various speech processing tasks, such as transcription, voice assistant applications, and more.

$-/run

6.4K

Huggingface

wav2vec2_tiny_random_robust

patrickvonplaten

The wav2vec2_tiny_random_robust is a feature extraction model that converts audio waveforms into a sequence of feature vectors. It is a smaller and randomized version of the wav2vec2 model and is designed to be more resilient to noise and other distortions in the audio signal.

$-/run

5.8K

Huggingface

tiny-wav2vec2-no-tokenizer

patrickvonplaten