Update examples/quantization_aware_training/torch/anomalib/README.md

Co-authored-by: Daniil Lyakhov <[email protected]>

examples/quantization_aware_training/torch/anomalib/README.md

@@ -4,7 +4,7 @@ The anomaly detection domain is one of the domains in which models are used in s
 
 This example demonstrates how to quantize [Student-Teacher Feature Pyramid Matching (STFPM)](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/stfpm.html) PyTorch model from [Anomalib](https://github.com/openvinotoolkit/anomalib) using Quantization API from Neural Network Compression Framework (NNCF). At the first step, the model is quanitzed using Post-Training Quantization (PTQ) algorithm to obtain the best initialization of the quantized model. If the accuracy of the quantized model after PTQ does not meet requiremenets, the next step is to train the quantized model using PyTorch framework.
 
-NNCF provides semiless transition from Post-Training Quantization to Quantization-Aware Training without additional model preparation and transfer of magic parameters.
+NNCF provides seamless transition from Post-Training Quantization to Quantization-Aware Training without additional model preparation and transfer of magic parameters.
 
 The example includes the following steps: