update colab env

Author: MahmoudAshraf97

Whisper_Transcription_+_NeMo_Diarization.ipynb

@@ -29,11 +29,12 @@
    },
    "outputs": [],
    "source": [
-    "!pip install faster-whisper>=1.1.0 ctranslate2==4.4.0\n",
+    "!pip install \"faster-whisper>=1.1.0\"\n",
     "!pip install \"nemo-toolkit[asr]>=2.dev\"\n",
     "!pip install git+https://github.com/MahmoudAshraf97/demucs.git\n",
     "!pip install git+https://github.com/oliverguhr/deepmultilingualpunctuation.git\n",
-    "!pip install git+https://github.com/MahmoudAshraf97/ctc-forced-aligner.git"
+    "!pip install git+https://github.com/MahmoudAshraf97/ctc-forced-aligner.git\n",
+    "!pip uninstall -y nvidia-cudnn-cu12"
    ]
   },
   {
@@ -712,7 +713,7 @@
     "# Whether to enable music removal from speech, helps increase diarization quality but uses alot of ram\n",
     "enable_stemming = True\n",
     "\n",
-    "# (choose from 'tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large')\n",
+    "# (choose from 'tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'turbo')\n",
     "whisper_model_name = \"large-v2\"\n",
     "\n",
     "# replaces numerical digits with their pronounciation, increases diarization accuracy\n",