Merge branch 'r2.0.0rc0' of github.com:NVIDIA/NeMo into r2.0.0rc0

Author: ericharper

.github/workflows/cicd-main.yml

@@ -247,7 +247,7 @@ Use this installation mode if you want the latest released version.
 .. code-block:: bash
 
     apt-get update && apt-get install -y libsndfile1 ffmpeg
-    pip install Cython
+    pip install Cython packaging
     pip install nemo_toolkit['all']
 
 Depending on the shell used, you may need to use ``"nemo_toolkit[all]"`` instead in the above command.
@@ -272,7 +272,7 @@ Use this installation mode if you want the version from a particular GitHub bran
 .. code-block:: bash
 
     apt-get update && apt-get install -y libsndfile1 ffmpeg
-    pip install Cython
+    pip install Cython packaging
     python -m pip install git+https://github.com/NVIDIA/NeMo.git@{BRANCH}#egg=nemo_toolkit[all]
 
 
@@ -310,7 +310,7 @@ To install NeMo on Mac with Apple M-Series GPU:
     conda install -c conda-forge pynini
 
     # install Cython manually
-    pip install cython
+    pip install cython packaging
 
     # clone the repo and install in development mode
     git clone https://github.com/NVIDIA/NeMo

README.rst

@@ -80,6 +80,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling parameters
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/cache_aware_streaming/fastconformer_ctc_bpe_streaming.yaml

@@ -78,6 +78,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling params
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/cache_aware_streaming/fastconformer_ctc_char_streaming.yaml

@@ -85,6 +85,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling parameters
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/cache_aware_streaming/fastconformer_transducer_bpe_streaming.yaml

@@ -84,6 +84,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling params
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/cache_aware_streaming/fastconformer_transducer_char_streaming.yaml

@@ -90,6 +90,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling parameters
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/hybrid_cache_aware_streaming/fastconformer_hybrid_transducer_ctc_bpe_streaming.yaml

@@ -88,6 +88,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling params
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/hybrid_cache_aware_streaming/fastconformer_hybrid_transducer_ctc_char_streaming.yaml

@@ -87,6 +87,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling parameters
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding

examples/asr/conf/fastconformer/hybrid_transducer_ctc/fastconformer_hybrid_transducer_ctc_bpe.yaml

@@ -85,6 +85,7 @@ model:
     feat_out: -1 # you may set it if you need different output size other than the default d_model
     n_layers: 17
     d_model: 512
+    use_bias: True # whether to apply bias in the feedforward, MHA and convolution modules
 
     # Sub-sampling params
     subsampling: dw_striding # vggnet, striding, stacking or stacking_norm, dw_striding