Add local support for audio models (PR #7329) (#7591)

- Description: run the poetry dependencies
  - Issue: #7329 
  - Dependencies: any dependencies required for this change,
  - Tag maintainer: @rlancemartin

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>

docs/extras/integrations/document_loaders/youtube_audio.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "e48afb8d",
    "metadata": {},
@@ -11,7 +12,8 @@
     "\n",
     "Below we show how to easily go from a YouTube url to text to chat!\n",
     "\n",
-    "We wil use the `OpenAIWhisperParser`, which will use the OpenAI Whisper API to transcribe audio to text.\n",
+    "We wil use the `OpenAIWhisperParser`, which will use the OpenAI Whisper API to transcribe audio to text, \n",
+    "and the  `OpenAIWhisperParserLocal` for local support and running on private clouds or on premise.\n",
     "\n",
     "Note: You will need to have an `OPENAI_API_KEY` supplied."
    ]
@@ -24,7 +26,7 @@
    "outputs": [],
    "source": [
     "from langchain.document_loaders.generic import GenericLoader\n",
-    "from langchain.document_loaders.parsers import OpenAIWhisperParser\n",
+    "from langchain.document_loaders.parsers import OpenAIWhisperParser, OpenAIWhisperParserLocal\n",
     "from langchain.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader"
    ]
   },
@@ -46,7 +48,8 @@
    "outputs": [],
    "source": [
     "! pip install yt_dlp\n",
-    "! pip install pydub"
+    "! pip install pydub\n",
+    "! pip install librosa"
    ]
   },
   {
@@ -63,6 +66,18 @@
     "Let's take the first lecture of Andrej Karpathy's YouTube course as an example! "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8682f256",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# set a flag to switch between local and remote parsing\n",
+    "# change this to True if you want to use local parsing\n",
+    "local = False"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -102,7 +117,10 @@
     "save_dir = \"~/Downloads/YouTube\"\n",
     "\n",
     "# Transcribe the videos to text\n",
-    "loader = GenericLoader(YoutubeAudioLoader(urls, save_dir), OpenAIWhisperParser())\n",
+    "if local:\n",
+    "    loader = GenericLoader(YoutubeAudioLoader(urls, save_dir), OpenAIWhisperParserLocal())\n",
+    "else:\n",
+    "    loader = GenericLoader(YoutubeAudioLoader(urls, save_dir), OpenAIWhisperParser())\n",
     "docs = loader.load()"
    ]
   },
@@ -275,7 +293,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -289,7 +307,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.11"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "97cc609b13305c559618ec78a438abc56230b9381f827f22d070313b9a1f3777"
+   }
   }
  },
  "nbformat": 4,