| --- |
| license: apache-2.0 |
| language: |
| - zh |
| - en |
| - yue |
| - ja |
| - ko |
| tags: |
| - automatic-speech-recognition |
| - speech |
| - audio |
| - encoder |
| - sensevoice |
| pipeline_tag: automatic-speech-recognition |
| --- |
| |
| # SenseVoiceSmall |
|
|
| This directory contains a local copy of [SenseVoiceSmall](https://www.modelscope.cn/iic/SenseVoiceSmall), released by the FunAudioLLM team. The model is used as a speech encoder / speech recognition component, while the original model architecture, weights, authorship, and license remain attributed to the original authors. |
|
|
| The original SenseVoiceSmall model is released under the `Apache-2.0` license. When using, redistributing, or citing these files, please keep the original author information, model link, and license notice. |
|
|
| Original links: |
|
|
| - ModelScope: https://www.modelscope.cn/iic/SenseVoiceSmall |
| - License: https://www.apache.org/licenses/LICENSE-2.0 |
|
|
