fix Online_ASR_Microphone_Demo_Buffered_Streaming.ipynb failed with ConfigKeyError (#15964)

* add confidences to beam search + cache_aware in streaming inference

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* clean up

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* add logging frame confidence

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* clean up

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* clean up

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* minor clean up

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* clean uo

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* minor changes

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* fix tests

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* minor fix

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* revert compute_metrics_per_sample argument

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* fix

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* fix preprocessor

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

* clean up

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

---------

Signed-off-by: lilithgrigoryan <lgrigoryan@nvidia.com>

Author: lilithgrigoryan

tutorials/asr/Online_ASR_Microphone_Demo_Buffered_Streaming.ipynb

@@ -16,7 +16,9 @@
     "3. Connect to an instance with a GPU (Runtime -> Change runtime type -> select \"GPU\" for hardware accelerator)\n",
     "4. Run this cell to set up dependencies.\n",
     "5. Set up microphone for Colab\n",
-    "\n\nNOTE: User is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use.\n",
+    "\n",
+    "\n",
+    "NOTE: User is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use.\n",
     "\"\"\"\n",
     "# If you're using Google Colab and not running locally, run this cell.\n",
     "\n",
@@ -150,45 +152,6 @@
     "cfg.preprocessor.dither = 0.0\n",
     "cfg.preprocessor.pad_to = 0\n",
     "\n",
-    "# spectrogram normalization constants\n",
-    "normalization = {}\n",
-    "normalization['fixed_mean'] = [\n",
-    "     -14.95827016, -12.71798736, -11.76067913, -10.83311182,\n",
-    "     -10.6746914,  -10.15163465, -10.05378331, -9.53918999,\n",
-    "     -9.41858904,  -9.23382904,  -9.46470918,  -9.56037,\n",
-    "     -9.57434245,  -9.47498732,  -9.7635205,   -10.08113074,\n",
-    "     -10.05454561, -9.81112681,  -9.68673603,  -9.83652977,\n",
-    "     -9.90046248,  -9.85404766,  -9.92560366,  -9.95440354,\n",
-    "     -10.17162966, -9.90102482,  -9.47471025,  -9.54416855,\n",
-    "     -10.07109475, -9.98249912,  -9.74359465,  -9.55632283,\n",
-    "     -9.23399915,  -9.36487649,  -9.81791084,  -9.56799225,\n",
-    "     -9.70630899,  -9.85148006,  -9.8594418,   -10.01378735,\n",
-    "     -9.98505315,  -9.62016094,  -10.342285,   -10.41070709,\n",
-    "     -10.10687659, -10.14536695, -10.30828702, -10.23542833,\n",
-    "     -10.88546868, -11.31723646, -11.46087382, -11.54877829,\n",
-    "     -11.62400934, -11.92190509, -12.14063815, -11.65130117,\n",
-    "     -11.58308531, -12.22214663, -12.42927197, -12.58039805,\n",
-    "     -13.10098969, -13.14345864, -13.31835645, -14.47345634]\n",
-    "normalization['fixed_std'] = [\n",
-    "     3.81402054, 4.12647781, 4.05007065, 3.87790987,\n",
-    "     3.74721178, 3.68377423, 3.69344,    3.54001005,\n",
-    "     3.59530412, 3.63752368, 3.62826417, 3.56488469,\n",
-    "     3.53740577, 3.68313898, 3.67138151, 3.55707266,\n",
-    "     3.54919572, 3.55721289, 3.56723346, 3.46029304,\n",
-    "     3.44119672, 3.49030548, 3.39328435, 3.28244406,\n",
-    "     3.28001423, 3.26744937, 3.46692348, 3.35378948,\n",
-    "     2.96330901, 2.97663111, 3.04575148, 2.89717604,\n",
-    "     2.95659301, 2.90181116, 2.7111687,  2.93041291,\n",
-    "     2.86647897, 2.73473181, 2.71495654, 2.75543763,\n",
-    "     2.79174615, 2.96076456, 2.57376336, 2.68789782,\n",
-    "     2.90930817, 2.90412004, 2.76187531, 2.89905006,\n",
-    "     2.65896173, 2.81032176, 2.87769857, 2.84665271,\n",
-    "     2.80863137, 2.80707634, 2.83752184, 3.01914511,\n",
-    "     2.92046439, 2.78461139, 2.90034605, 2.94599508,\n",
-    "     2.99099718, 3.0167554,  3.04649716, 2.94116777]\n",
-    "\n",
-    "cfg.preprocessor.normalize = normalization\n",
-    "\n",
     "# Disable config overwriting\n",
     "OmegaConf.set_struct(cfg.preprocessor, True)"
    ]
@@ -344,8 +307,7 @@
     "        self.frame_overlap = frame_overlap\n",
     "        self.n_frame_overlap = int(frame_overlap * self.sr)\n",
     "        timestep_duration = model_definition['AudioToMelSpectrogramPreprocessor']['window_stride']\n",
-    "        for block in model_definition['JasperEncoder']['jasper']:\n",
-    "            timestep_duration *= block['stride'][0] ** block['repeat']\n",
+    "        timestep_duration *= model_definition['JasperEncoder']['subsampling_factor']\n",
     "        self.n_timesteps_overlap = int(frame_overlap / timestep_duration) - 2\n",
     "        self.buffer = np.zeros(shape=2*self.n_frame_overlap + self.n_frame_len,\n",
     "                               dtype=np.float32)\n",
@@ -519,4 +481,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}