Manh Dat Tran

Inference results are different on different computers

4

### Bug Description when i inference model converted (streaming convnet) and use the same converted model, options and audio files; the results are different on different computer. #### Reproduction Steps...

Simple Streaming ASR Example for Sota/2019 Model

5

### Feature Description A detail example about Running streaming ASR with sota/2019 model on custom trained model #### Use Case [Current Streaming ASR Example](https://github.com/facebookresearch/wav2letter/wiki/Inference-Run-Examples#simple-streaming-asr-example) requires acoustic_model.bin, feature_extractor.bin, tokens.txt which come...

i have 2 questions, First, is wav2vec lastest model you implement better than wav2vec + wav2letter ( for example in wer, recognition in reality?) Second, can you provide tutorial for...

### System Info ```shell OS: Ubuntu 20.04.4 LTS CARD: RTX 3080 Libs: python 3.10.4 onnx==1.12.0 onnxruntime-gpu==1.12.1 torch==1.12.1 transformers==4.21.2 ``` ### Who can help? @lewtun @michaelbenayoun @JingyaHuang @echarlaix ### Information -...

when you compare 2 embbeding by feature compare function,why using np.dot for 2 numpy array 1D,it seem return sum of ( element * element) of 2 numpy array i dont...