This commit is contained in:
北念 2024-06-27 20:50:40 +08:00
parent fbe5bf1d21
commit a29026cee4
3 changed files with 23 additions and 0 deletions

View File

@ -159,5 +159,28 @@ git clone https://www.modelscope.cn/iic/SenseVoiceSmall.git
Undo Undo
# Performance
## 语音识别效果
我们在开源基准数据集(包括 AISHELL-1、AISHELL-2、Wenetspeech、Librispeech和Common Voice上比较了SenseVoice与Whisper的多语言语音识别性能和推理效率。在中文和粤语识别效果上SenseVoice-Small模型具有明显的效果优势。
<p align="center">
<img src="fig/asr_results.png" alt="SenseVoice模型在开源测试集上的表现" width="500" />
</p>
## 情感识别效果
## 事件检测效果
## 推理效率
SenseVoice-small模型采用非自回归端到端架构推理延迟极低。在参数量与Whisper-Small模型相当的情况下比Whisper-Small模型推理速度快7倍比Whisper-Large模型快17倍。同时SenseVoice-small模型在音频时长增加的情况下推理耗时也无明显增加。
<p align="center">
<img src="fig/inference.png" alt="SenseVoice模型的推理效率" width="500" />
</p>
<p style="color: lightgrey;">如果您是本模型的贡献者,我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>,及时完善模型卡片内容。</p> <p style="color: lightgrey;">如果您是本模型的贡献者,我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>,及时完善模型卡片内容。</p>

BIN
fig/asr_results.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 238 KiB

BIN
fig/inference.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 470 KiB