返回全部动态
React Native ExecuTorch 发布 whisper-tiny 语音识别模型
原标题：software-mansion/react-native-executorch-whisper-tiny
AI 摘要
Hugging Face 上发布了 whisper-tiny 模型，专为 React Native ExecuTorch 库设计，提供 XNNPACK、CoreML 和 MLX 后端的 .pte 格式导出。模型使用 ExecuTorch v1.2.0 导出，不保证向前兼容，用户需确保运行时版本匹配。该模型可用于自动语音识别任务。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
--- license: apache-2.0 pipeline_tag: automatic-speech-recognition --- # Introduction This repository hosts the [whisper-tiny](https://huggingface.co/openai/whisper-tiny) model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes the model exported for XNNPACK, CoreML and MLX backends in `.pte` format, ready for use in the **ExecuTorch** runtime. If you'd like to run these models in your own ExecuTorch runtime, refer to the [official do
发布时间：2026-08-03 23:48
抓取时间：2026-08-03 23:49
来源机构：Hugging Face