Enable quantization for wav2letter (#446)

Summary:

X-link: pytorch/pytorch#109830

Also added annotation support for conv1d_relu and conv1d in XNNPACKQuantizer, the quantized results still
matches fx quant path (didn't quantize conv1d) so tests are not disabled

Reviewed By: kimishpatel

Differential Revision: D49479546

Author: jerryzh168

examples/recipes/xnnpack_optimization/models.py

@@ -25,7 +25,7 @@ class OptimizationOptions(object):
     "resnet18": OptimizationOptions(True, True),
     "resnet50": OptimizationOptions(True, True),
     "vit": OptimizationOptions(False, True),
-    "w2l": OptimizationOptions(False, True),
+    "w2l": OptimizationOptions(True, True),
     "edsr": OptimizationOptions(True, False),
     "mobilebert": OptimizationOptions(True, False),
 }