ASR Notebooks fix for 1.1.0 (#2395)

* nb fix for spring clean Signed-off-by: fayejf <[email protected]> * remove outdated instruction Signed-off-by: fayejf <[email protected]>
NVIDIA · Jun 24, 2021 · 4880f7d · 4880f7d
1 parent c146867
commit 4880f7d
Show file tree

Hide file tree

Showing 7 changed files with 21 additions and 36 deletions.
diff --git a/tutorials/asr/03_Speech_Commands.ipynb b/tutorials/asr/03_Speech_Commands.ipynb
@@ -333,7 +333,7 @@
    "source": [
     "# Preserve some useful parameters\n",
     "labels = config.model.labels\n",
-    "sample_rate = config.sample_rate"
+    "sample_rate = config.model.sample_rate"
    ],
    "execution_count": null,
    "outputs": []
@@ -1625,4 +1625,4 @@
    ]
   }
  ]
-}
+}
diff --git a/tutorials/asr/04_Online_Offline_Speech_Commands_Demo.ipynb b/tutorials/asr/04_Online_Offline_Speech_Commands_Demo.ipynb
@@ -39,11 +39,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "\n",
-    "This notebook demonstrates offline and online (from a microphone's stream in NeMo) speech commands recognition \n",
-    "\n",
-    "It is **not a recommended** way to do inference in production workflows. If you are interested in \n",
-    "production-level inference using NeMo ASR models, please sign-up to Jarvis early access program: https://developer.nvidia.com/nvidia-jarvis"
+    "This notebook demonstrates offline and online (from a microphone's stream in NeMo) speech commands recognition "
    ]
   },
   {

diff --git a/tutorials/asr/05_Online_Noise_Augmentation.ipynb b/tutorials/asr/05_Online_Noise_Augmentation.ipynb
@@ -334,7 +334,7 @@
    "outputs": [],
    "source": [
     "# Import the data augmentation component from ASR collection\n",
-    "from nemo.collections.asr.parts import perturb, segment"
+    "from nemo.collections.asr.parts.preprocessing import perturb, segment"
    ]
   },
   {
@@ -1188,7 +1188,7 @@
    "outputs": [],
    "source": [
     "# We use a NeMo utility to parse the manifest file for us\n",
-    "from nemo.collections.asr.parts import collections, parsers\n",
+    "from nemo.collections.common.parts.preprocessing import collections, parsers\n",
     "\n",
     "class NoisePerturbationEval(perturb.Perturbation):\n",
     "    def __init__(\n",
@@ -1303,18 +1303,18 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.7.7"
   },
   "pycharm": {
    "stem_cell": {
     "cell_type": "raw",
-    "source": [],
     "metadata": {
      "collapsed": false
-    }
+    },
+    "source": []
    }
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}
diff --git a/tutorials/asr/06_Voice_Activiy_Detection.ipynb b/tutorials/asr/06_Voice_Activiy_Detection.ipynb
@@ -329,7 +329,7 @@
    "source": [
     "# Preserve some useful parameters\n",
     "labels = config.model.labels\n",
-    "sample_rate = config.sample_rate"
+    "sample_rate = config.model.sample_rate"
    ]
   },
   {
@@ -1157,13 +1157,13 @@
   "pycharm": {
    "stem_cell": {
     "cell_type": "raw",
-    "source": [],
     "metadata": {
      "collapsed": false
-    }
+    },
+    "source": []
    }
   }
  },
  "nbformat": 4,
  "nbformat_minor": 1
-}
+}
diff --git a/tutorials/asr/07_Online_Offline_Microphone_VAD_Demo.ipynb b/tutorials/asr/07_Online_Offline_Microphone_VAD_Demo.ipynb
@@ -45,11 +45,7 @@
     "2. [finetuning](#Finetune) and use [posterior](#Posterior);\n",
     "2. [threshold tuning](#Tuning-threshold);\n",
     "4. [online streaming inference](#Online-streaming-inference);\n",
-    "3. [online streaming inference from a microphone's stream](#Online-streaming-inference-through-microphone).\n",
-    "\n",
-    "\n",
-    "It is **not a recommended** way to do inference in production workflows. If you are interested in \n",
-    "production-level inference using NeMo ASR models, please sign-up to Jarvis early access program: https://developer.nvidia.com/nvidia-jarvis"
+    "3. [online streaming inference from a microphone's stream](#Online-streaming-inference-through-microphone).\n"
    ]
   },
   {

diff --git a/tutorials/speaker_recognition/ASR_with_SpeakerDiarization.ipynb b/tutorials/speaker_recognition/ASR_with_SpeakerDiarization.ipynb
@@ -393,7 +393,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from nemo.collections.asr.parts.speaker_utils import write_rttm2manifest\n",
+    "from nemo.collections.asr.parts.utils.speaker_utils import write_rttm2manifest\n",
     "output_dir = os.path.join(ROOT, 'oracle_vad')\n",
     "os.makedirs(output_dir,exist_ok=True)\n",
     "oracle_manifest = os.path.join(output_dir,'oracle_manifest.json')\n",
@@ -466,7 +466,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from nemo.collections.asr.parts.speaker_utils import rttm_to_labels\n",
+    "from nemo.collections.asr.parts.utils.speaker_utils import rttm_to_labels\n",
     "pred_rttm=os.path.join(output_dir,'pred_rttms',uniq_id+'.rttm')\n",
     "labels=rttm_to_labels(pred_rttm)\n",
     "print(\"speaker labels with time stamps\\n\",labels)"
@@ -522,13 +522,6 @@
     "\n",
     "print(words[j+1],end=\" \")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -547,7 +540,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.10"
+   "version": "3.7.7"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/speaker_recognition/Speaker_Diarization_Inference.ipynb b/tutorials/speaker_recognition/Speaker_Diarization_Inference.ipynb
@@ -115,7 +115,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from nemo.collections.asr.parts.speaker_utils import rttm_to_labels, labels_to_pyannote_object"
+    "from nemo.collections.asr.parts.utils.speaker_utils import rttm_to_labels, labels_to_pyannote_object"
    ]
   },
   {
@@ -212,7 +212,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from nemo.collections.asr.parts.speaker_utils import write_rttm2manifest\n",
+    "from nemo.collections.asr.parts.utils.speaker_utils import write_rttm2manifest\n",
     "output_dir = os.path.join(ROOT, 'oracle_vad')\n",
     "os.makedirs(output_dir,exist_ok=True)"
    ]
@@ -485,7 +485,7 @@
    "outputs": [],
    "source": [
     "# VAD predicted time stamps\n",
-    "from nemo.collections.asr.parts.vad_utils import extract_labels, plot\n",
+    "from nemo.collections.asr.parts.utils.vad_utils import extract_labels, plot\n",
     "\n",
     "plot(paths2audio_files[0],\n",
     "     'outputs/vad_outputs/overlap_smoothing_output_median_0.875/an4_diarize_test.median', \n",
@@ -615,7 +615,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.10"
+   "version": "3.7.7"
   },
   "pycharm": {
    "stem_cell": {