Sew D Tiny 100k

🚀 SEW-D-tiny

The base model pretrained on 16kHz sampled speech audio, suitable for fine - tuning on various downstream speech tasks.

🚀 Quick Start

The base model is pretrained on 16kHz sampled speech audio. When using the model, ensure that your speech input is also sampled at 16Khz. Note that this model should be fine - tuned on a downstream task, such as Automatic Speech Recognition, Speaker Identification, Intent Classification, Emotion Recognition, etc.

The original model can be found under this link.

✨ Features

• SEW - D by ASAPP Research: Check it on GitHub
• Research Paper: Performance - Efficiency Trade - offs in Unsupervised Pre - training for Speech Recognition
  • Authors: Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi
• Abstract: This paper is a study of performance - efficiency trade - offs in pre - trained models for automatic speech recognition (ASR). It focuses on wav2vec 2.0 and formalizes several architecture designs that influence both the model performance and its efficiency. By integrating all observations, it introduces SEW (Squeezed and Efficient Wav2vec), a pre - trained model architecture with significant improvements in both performance and efficiency across various training setups. For example, under the 100h - 960h semi - supervised setup on LibriSpeech, SEW achieves a 1.9x inference speedup compared to wav2vec 2.0, with a 13.5% relative reduction in word error rate. With a similar inference time, SEW reduces the word error rate by 25 - 50% across different model sizes.

💻 Usage Examples

Basic Usage

See [this blog](https://huggingface.co/blog/fine - tune-wav2vec2-english) for more information on how to fine - tune the model. Note that the class Wav2Vec2ForCTC has to be replaced by SEWDForCTC.

📄 License

This project is licensed under the Apache 2.0 license.