geniusnut

### 详细描述问题 运行langchain_qa.py得到的效果不理想。 是训练模型的问题还是后期处理问题？应该使用什么手段解决问题？ ### 运行截图或日志 如下图所示。  ### 必查项目（前三项只保留你要问的） - [ ] **基础模型**：Alpaca-Plus-7B - [ ] **运行系统**：Windows - [ ] **问题分类**：效果问题 - [ ] （必选）由于相关依赖频繁更新，请确保按照[Wiki](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki)中的相关步骤执行 - [ ] （必选）我已阅读[FAQ章节](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/常见问题)并且已在Issue中对问题进行了搜索，没有找到相似问题和解决方案...

Sherpa-onnx Zipvoice pronounce "3" to "2"

3

Using the python-api-example ```bash python3 ./python-api-examples/offline-zeroshot-tts.py \ --zipvoice-flow-matching-model sherpa-onnx-zipvoice-distill-zh-en-emilia/fm_decoder.onnx \ --zipvoice-text-model sherpa-onnx-zipvoice-distill-zh-en-emilia/text_encoder.onnx \ --zipvoice-data-dir sherpa-onnx-zipvoice-distill-zh-en-emilia/espeak-ng-data \ --zipvoice-pinyin-dict sherpa-onnx-zipvoice-distill-zh-en-emilia/pinyin.raw \ --zipvoice-tokens sherpa-onnx-zipvoice-distill-zh-en-emilia/tokens.txt \ --zipvoice-vocoder sherpa-onnx-zipvoice-distill-zh-en-emilia/vocos_24khz.onnx \ --prompt-audio sherpa-onnx-zipvoice-distill-zh-en-emilia/prompt.wav \ --zipvoice-num-steps 4...

使用MNNConvert ```bash ../../build/MNNConvert -f ONNX --modelFile model.onnx --MNNModel model.mnn ``` 转换模型。 用 ```bash ./build/bin/sherpa-mnn-offline-tts \ --kokoro-model=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/model.mnn \ --kokoro-voices=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/voices.bin \ --kokoro-tokens=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/tokens.txt \ --kokoro-data-dir=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/espeak-ng-data \ --kokoro-dict-dir=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/dict \ --kokoro-lexicon=../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/lexicon-us-en.txt,../../../sherpa-mnn-models/kokoro-multi-lang-v1_1/lexicon-zh.txt \ --num-threads=2 \ --sid=10...