Committed by
GitHub
Update readme to include BreezeApp from MediaTek Research. (#2313)
See also https://github.com/mtkresearch/BreezeApp
正在显示
1 个修改的文件
包含
17 行增加
和
1 行删除
| @@ -277,6 +277,20 @@ for 新一代 Kaldi **微信交流群** and **QQ 交流群**. | @@ -277,6 +277,20 @@ for 新一代 Kaldi **微信交流群** and **QQ 交流群**. | ||
| 277 | 277 | ||
| 278 | ## Projects using sherpa-onnx | 278 | ## Projects using sherpa-onnx |
| 279 | 279 | ||
| 280 | +### [BreezeApp](https://github.com/mtkresearch/BreezeApp) from [MediaTek Research](https://github.com/mtkresearch) | ||
| 281 | + | ||
| 282 | +> BreezeAPP is a mobile AI application developed for both Android and iOS platforms. | ||
| 283 | +> Users can download it directly from the App Store and enjoy a variety of features | ||
| 284 | +> offline, including speech-to-text, text-to-speech, text-based chatbot interactions, | ||
| 285 | +> and image question-answering | ||
| 286 | + | ||
| 287 | + - [Download APK for BreezeAPP](https://huggingface.co/MediaTek-Research/BreezeApp/resolve/main/BreezeApp.apk) | ||
| 288 | + - [APK 中国镜像](https://hf-mirror.com/MediaTek-Research/BreezeApp/blob/main/BreezeApp.apk) | ||
| 289 | + | ||
| 290 | +| 1 | 2 | 3 | | ||
| 291 | +|---|---|---| | ||
| 292 | +|||| | ||
| 293 | + | ||
| 280 | ### [Open-LLM-VTuber](https://github.com/t41372/Open-LLM-VTuber) | 294 | ### [Open-LLM-VTuber](https://github.com/t41372/Open-LLM-VTuber) |
| 281 | 295 | ||
| 282 | Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking | 296 | Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking |
| @@ -358,7 +372,9 @@ It is a [YouTube video](https://www.youtube.com/watch?v=KxPKkwxGWZs), | @@ -358,7 +372,9 @@ It is a [YouTube video](https://www.youtube.com/watch?v=KxPKkwxGWZs), | ||
| 358 | showing how the author tried to use AI so he can have a conversation with Paimon. | 372 | showing how the author tried to use AI so he can have a conversation with Paimon. |
| 359 | 373 | ||
| 360 | It uses sherpa-onnx for speech-to-text and text-to-speech. | 374 | It uses sherpa-onnx for speech-to-text and text-to-speech. |
| 361 | - | 375 | +|1| |
| 376 | +|---| | ||
| 377 | +|| | ||
| 362 | 378 | ||
| 363 | [sherpa-rs]: https://github.com/thewh1teagle/sherpa-rs | 379 | [sherpa-rs]: https://github.com/thewh1teagle/sherpa-rs |
| 364 | [silero-vad]: https://github.com/snakers4/silero-vad | 380 | [silero-vad]: https://github.com/snakers4/silero-vad |
-
请 注册 或 登录 后发表评论