From 61db9810176d90377d9b1df8189037173a536600 Mon Sep 17 00:00:00 2001
From: Timothy Carambat <rambat1010@gmail.com>
Date: Fri, 15 Dec 2023 11:20:13 -0800
Subject: [PATCH] feat: Embed on-instance Whisper model for audio/mp4
 transcribing (#449)

* feat: Embed on-instance Whisper model for audio/mp4 transcribing
resolves #329

* additional logging

* add placeholder for tmp folder in collector storage
Add cleanup of hotdir and tmp on collector boot to prevent hanging files
split loading of model and file conversion into concurrency

* update README

* update model size

* update supported filetypes
---
 collector/index.js                            |   2 +
 collector/package.json                        |   7 +-
 .../processSingleFile/convert/asAudio.js      | 146 +++++++
 collector/storage/.gitignore                  |   2 +
 collector/storage/tmp/.placeholder            |   0
 .../utils/WhisperProviders/localWhisper.js    |  59 +++
 collector/utils/asDocx.js                     |  50 ---
 collector/utils/constants.js                  |  11 +
 collector/utils/files/index.js                |  40 ++
 collector/yarn.lock                           | 375 +++++++++++++++++-
 .../Documents/UploadFile/index.jsx            |   3 +-
 server/storage/models/README.md               |   5 +
 12 files changed, 636 insertions(+), 64 deletions(-)
 create mode 100644 collector/processSingleFile/convert/asAudio.js
 create mode 100644 collector/storage/.gitignore
 create mode 100644 collector/storage/tmp/.placeholder
 create mode 100644 collector/utils/WhisperProviders/localWhisper.js
 delete mode 100644 collector/utils/asDocx.js

diff --git a/collector/index.js b/collector/index.js
index a4506673..4cbca6c2 100644
--- a/collector/index.js
+++ b/collector/index.js
@@ -10,6 +10,7 @@ const { ACCEPTED_MIMES } = require("./utils/constants");
 const { reqBody } = require("./utils/http");
 const { processSingleFile } = require("./processSingleFile");
 const { processLink } = require("./processLink");
+const { wipeCollectorStorage } = require("./utils/files");
 const app = express();
 
 app.use(cors({ origin: true }));
@@ -66,6 +67,7 @@ app.all("*", function (_, response) {
 
 app
   .listen(8888, async () => {
+    await wipeCollectorStorage();
     console.log(`Document processor app listening on port 8888`);
   })
   .on("error", function (_) {
diff --git a/collector/package.json b/collector/package.json
index c85890d1..180a2088 100644
--- a/collector/package.json
+++ b/collector/package.json
@@ -10,18 +10,20 @@
     "node": ">=18.12.1"
   },
   "scripts": {
-    "dev": "NODE_ENV=development nodemon --trace-warnings index.js",
+    "dev": "NODE_ENV=development nodemon --ignore hotdir --ignore storage --trace-warnings index.js",
     "start": "NODE_ENV=production node index.js",
     "lint": "yarn prettier --write ./processSingleFile ./processLink ./utils index.js"
   },
   "dependencies": {
     "@googleapis/youtube": "^9.0.0",
+    "@xenova/transformers": "^2.11.0",
     "bcrypt": "^5.1.0",
     "body-parser": "^1.20.2",
     "cors": "^2.8.5",
     "dotenv": "^16.0.3",
     "express": "^4.18.2",
     "extract-zip": "^2.0.1",
+    "fluent-ffmpeg": "^2.1.2",
     "js-tiktoken": "^1.0.8",
     "langchain": "0.0.201",
     "mammoth": "^1.6.0",
@@ -33,7 +35,8 @@
     "pdf-parse": "^1.1.1",
     "puppeteer": "^21.6.1",
     "slugify": "^1.6.6",
-    "uuid": "^9.0.0"
+    "uuid": "^9.0.0",
+    "wavefile": "^11.0.0"
   },
   "devDependencies": {
     "nodemon": "^2.0.22",
diff --git a/collector/processSingleFile/convert/asAudio.js b/collector/processSingleFile/convert/asAudio.js
new file mode 100644
index 00000000..97e958df
--- /dev/null
+++ b/collector/processSingleFile/convert/asAudio.js
@@ -0,0 +1,146 @@
+const fs = require("fs");
+const path = require("path");
+const { v4 } = require("uuid");
+const {
+  createdDate,
+  trashFile,
+  writeToServerDocuments,
+} = require("../../utils/files");
+const { tokenizeString } = require("../../utils/tokenizer");
+const { default: slugify } = require("slugify");
+const { LocalWhisper } = require("../../utils/WhisperProviders/localWhisper");
+
+async function asAudio({ fullFilePath = "", filename = "" }) {
+  const whisper = new LocalWhisper();
+
+  console.log(`-- Working ${filename} --`);
+  const transcriberPromise = new Promise((resolve) =>
+    whisper.client().then((client) => resolve(client))
+  );
+  const audioDataPromise = new Promise((resolve) =>
+    convertToWavAudioData(fullFilePath).then((audioData) => resolve(audioData))
+  );
+  const [audioData, transcriber] = await Promise.all([
+    audioDataPromise,
+    transcriberPromise,
+  ]);
+
+  if (!audioData) {
+    console.error(`Failed to parse content from ${filename}.`);
+    trashFile(fullFilePath);
+    return {
+      success: false,
+      reason: `Failed to parse content from ${filename}.`,
+    };
+  }
+
+  console.log(`[Model Working]: Transcribing audio data to text`);
+  const { text: content } = await transcriber(audioData, {
+    chunk_length_s: 30,
+    stride_length_s: 5,
+  });
+
+  if (!content.length) {
+    console.error(`Resulting text content was empty for ${filename}.`);
+    trashFile(fullFilePath);
+    return { success: false, reason: `No text content found in ${filename}.` };
+  }
+
+  data = {
+    id: v4(),
+    url: "file://" + fullFilePath,
+    title: filename,
+    docAuthor: "no author found",
+    description: "No description found.",
+    docSource: "pdf file uploaded by the user.",
+    chunkSource: filename,
+    published: createdDate(fullFilePath),
+    wordCount: content.split(" ").length,
+    pageContent: content,
+    token_count_estimate: tokenizeString(content).length,
+  };
+
+  writeToServerDocuments(data, `${slugify(filename)}-${data.id}`);
+  trashFile(fullFilePath);
+  console.log(
+    `[SUCCESS]: ${filename} transcribed, converted & ready for embedding.\n`
+  );
+  return { success: true, reason: null };
+}
+
+async function convertToWavAudioData(sourcePath) {
+  try {
+    let buffer;
+    const wavefile = require("wavefile");
+    const ffmpeg = require("fluent-ffmpeg");
+    const outFolder = path.resolve(__dirname, `../../storage/tmp`);
+    if (!fs.existsSync(outFolder)) fs.mkdirSync(outFolder, { recursive: true });
+
+    const fileExtension = path.extname(sourcePath).toLowerCase();
+    if (fileExtension !== ".wav") {
+      console.log(
+        `[Conversion Required] ${fileExtension} file detected - converting to .wav`
+      );
+      const outputFile = path.resolve(outFolder, `${v4()}.wav`);
+      const convert = new Promise((resolve) => {
+        ffmpeg(sourcePath)
+          .toFormat("wav")
+          .on("error", (error) => {
+            console.error(`[Conversion Error] ${error.message}`);
+            resolve(false);
+          })
+          .on("progress", (progress) =>
+            console.log(
+              `[Conversion Processing]: ${progress.targetSize}KB converted`
+            )
+          )
+          .on("end", () => {
+            console.log("[Conversion Complete]: File converted to .wav!");
+            resolve(true);
+          })
+          .save(outputFile);
+      });
+      const success = await convert;
+      if (!success)
+        throw new Error(
+          "[Conversion Failed]: Could not convert file to .wav format!"
+        );
+
+      const chunks = [];
+      const stream = fs.createReadStream(outputFile);
+      for await (let chunk of stream) chunks.push(chunk);
+      buffer = Buffer.concat(chunks);
+      fs.rmSync(outputFile);
+    } else {
+      const chunks = [];
+      const stream = fs.createReadStream(sourcePath);
+      for await (let chunk of stream) chunks.push(chunk);
+      buffer = Buffer.concat(chunks);
+    }
+
+    const wavFile = new wavefile.WaveFile(buffer);
+    wavFile.toBitDepth("32f");
+    wavFile.toSampleRate(16000);
+
+    let audioData = wavFile.getSamples();
+    if (Array.isArray(audioData)) {
+      if (audioData.length > 1) {
+        const SCALING_FACTOR = Math.sqrt(2);
+
+        // Merge channels into first channel to save memory
+        for (let i = 0; i < audioData[0].length; ++i) {
+          audioData[0][i] =
+            (SCALING_FACTOR * (audioData[0][i] + audioData[1][i])) / 2;
+        }
+      }
+      audioData = audioData[0];
+    }
+
+    return audioData;
+  } catch (error) {
+    console.error(`convertToWavAudioData`, error);
+    return null;
+  }
+}
+
+module.exports = asAudio;
diff --git a/collector/storage/.gitignore b/collector/storage/.gitignore
new file mode 100644
index 00000000..845482b7
--- /dev/null
+++ b/collector/storage/.gitignore
@@ -0,0 +1,2 @@
+tmp/*
+!tmp/.placeholder
\ No newline at end of file
diff --git a/collector/storage/tmp/.placeholder b/collector/storage/tmp/.placeholder
new file mode 100644
index 00000000..e69de29b
diff --git a/collector/utils/WhisperProviders/localWhisper.js b/collector/utils/WhisperProviders/localWhisper.js
new file mode 100644
index 00000000..6503e202
--- /dev/null
+++ b/collector/utils/WhisperProviders/localWhisper.js
@@ -0,0 +1,59 @@
+const path = require("path");
+const fs = require("fs");
+
+class LocalWhisper {
+  constructor() {
+    // Model Card: https://huggingface.co/Xenova/whisper-small
+    this.model = "Xenova/whisper-small";
+    this.cacheDir = path.resolve(
+      process.env.STORAGE_DIR
+        ? path.resolve(process.env.STORAGE_DIR, `models`)
+        : path.resolve(__dirname, `../../../server/storage/models`)
+    );
+
+    this.modelPath = path.resolve(this.cacheDir, "Xenova", "whisper-small");
+
+    // Make directory when it does not exist in existing installations
+    if (!fs.existsSync(this.cacheDir))
+      fs.mkdirSync(this.cacheDir, { recursive: true });
+  }
+
+  async client() {
+    if (!fs.existsSync(this.modelPath)) {
+      console.log(
+        "\x1b[34m[INFO]\x1b[0m The native whisper model has never been run and will be downloaded right now. Subsequent runs will be faster. (~250MB)\n\n"
+      );
+    }
+
+    try {
+      // Convert ESM to CommonJS via import so we can load this library.
+      const pipeline = (...args) =>
+        import("@xenova/transformers").then(({ pipeline }) =>
+          pipeline(...args)
+        );
+      return await pipeline("automatic-speech-recognition", this.model, {
+        cache_dir: this.cacheDir,
+        ...(!fs.existsSync(this.modelPath)
+          ? {
+              // Show download progress if we need to download any files
+              progress_callback: (data) => {
+                if (!data.hasOwnProperty("progress")) return;
+                console.log(
+                  `\x1b[34m[Embedding - Downloading Model Files]\x1b[0m ${
+                    data.file
+                  } ${~~data?.progress}%`
+                );
+              },
+            }
+          : {}),
+      });
+    } catch (error) {
+      console.error("Failed to load the native whisper model:", error);
+      throw error;
+    }
+  }
+}
+
+module.exports = {
+  LocalWhisper,
+};
diff --git a/collector/utils/asDocx.js b/collector/utils/asDocx.js
deleted file mode 100644
index cd81a5a5..00000000
--- a/collector/utils/asDocx.js
+++ /dev/null
@@ -1,50 +0,0 @@
-const { v4 } = require("uuid");
-const { DocxLoader } = require("langchain/document_loaders/fs/docx");
-const {
-  createdDate,
-  trashFile,
-  writeToServerDocuments,
-} = require("../../utils/files");
-const { tokenizeString } = require("../../utils/tokenizer");
-const { default: slugify } = require("slugify");
-
-async function asDocX({ fullFilePath = "", filename = "" }) {
-  const loader = new DocxLoader(fullFilePath);
-
-  console.log(`-- Working ${filename} --`);
-  let pageContent = [];
-  const docs = await loader.load();
-  for (const doc of docs) {
-    console.log(doc.metadata);
-    console.log(`-- Parsing content from docx page --`);
-    if (!doc.pageContent.length) continue;
-    pageContent.push(doc.pageContent);
-  }
-
-  if (!pageContent.length) {
-    console.error(`Resulting text content was empty for ${filename}.`);
-    return { success: false, reason: `No text content found in ${filename}.` };
-  }
-
-  const content = pageContent.join("");
-  data = {
-    id: v4(),
-    url: "file://" + fullFilePath,
-    title: filename,
-    docAuthor: "no author found",
-    description: "No description found.",
-    docSource: "pdf file uploaded by the user.",
-    chunkSource: filename,
-    published: createdDate(fullFilePath),
-    wordCount: content.split(" ").length,
-    pageContent: content,
-    token_count_estimate: tokenizeString(content).length,
-  };
-
-  writeToServerDocuments(data, `${slugify(filename)}-${data.id}`);
-  trashFile(fullFilePath);
-  console.log(`[SUCCESS]: ${filename} converted & ready for embedding.\n`);
-  return { success: true, reason: null };
-}
-
-module.exports = asDocX;
diff --git a/collector/utils/constants.js b/collector/utils/constants.js
index ca59836c..31da29e5 100644
--- a/collector/utils/constants.js
+++ b/collector/utils/constants.js
@@ -16,6 +16,12 @@ const ACCEPTED_MIMES = {
 
   "application/pdf": [".pdf"],
   "application/mbox": [".mbox"],
+
+  "audio/wav": [".wav"],
+  "audio/mpeg": [".mp3"],
+
+  "video/mp4": [".mp4"],
+  "video/mpeg": [".mpeg"],
 };
 
 const SUPPORTED_FILETYPE_CONVERTERS = {
@@ -31,6 +37,11 @@ const SUPPORTED_FILETYPE_CONVERTERS = {
   ".odp": "./convert/asOfficeMime.js",
 
   ".mbox": "./convert/asMbox.js",
+
+  ".mp3": "./convert/asAudio.js",
+  ".wav": "./convert/asAudio.js",
+  ".mp4": "./convert/asAudio.js",
+  '.mpeg': "./convert/asAudio.js",
 };
 
 module.exports = {
diff --git a/collector/utils/files/index.js b/collector/utils/files/index.js
index edcdd54f..915c4ac1 100644
--- a/collector/utils/files/index.js
+++ b/collector/utils/files/index.js
@@ -48,8 +48,48 @@ function writeToServerDocuments(
   return;
 }
 
+// When required we can wipe the entire collector hotdir and tmp storage in case
+// there were some large file failures that we unable to be removed a reboot will
+// force remove them.
+async function wipeCollectorStorage() {
+  const cleanHotDir = new Promise((resolve) => {
+    const directory = path.resolve(__dirname, "../../hotdir");
+    fs.readdir(directory, (err, files) => {
+      if (err) resolve();
+
+      for (const file of files) {
+        if (file === "__HOTDIR__.md") continue;
+        try {
+          fs.rmSync(path.join(directory, file));
+        } catch {}
+      }
+      resolve();
+    });
+  });
+
+  const cleanTmpDir = new Promise((resolve) => {
+    const directory = path.resolve(__dirname, "../../storage/tmp");
+    fs.readdir(directory, (err, files) => {
+      if (err) resolve();
+
+      for (const file of files) {
+        if (file === ".placeholder") continue;
+        try {
+          fs.rmSync(path.join(directory, file));
+        } catch {}
+      }
+      resolve();
+    });
+  });
+
+  await Promise.all([cleanHotDir, cleanTmpDir]);
+  console.log(`Collector hot directory and tmp storage wiped!`);
+  return;
+}
+
 module.exports = {
   trashFile,
   createdDate,
   writeToServerDocuments,
+  wipeCollectorStorage,
 };
diff --git a/collector/yarn.lock b/collector/yarn.lock
index b277d7ac..c6f442a8 100644
--- a/collector/yarn.lock
+++ b/collector/yarn.lock
@@ -76,6 +76,59 @@
     semver "^7.3.5"
     tar "^6.1.11"
 
+"@protobufjs/aspromise@^1.1.1", "@protobufjs/aspromise@^1.1.2":
+  version "1.1.2"
+  resolved "https://registry.yarnpkg.com/@protobufjs/aspromise/-/aspromise-1.1.2.tgz#9b8b0cc663d669a7d8f6f5d0893a14d348f30fbf"
+  integrity sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ==
+
+"@protobufjs/base64@^1.1.2":
+  version "1.1.2"
+  resolved "https://registry.yarnpkg.com/@protobufjs/base64/-/base64-1.1.2.tgz#4c85730e59b9a1f1f349047dbf24296034bb2735"
+  integrity sha512-AZkcAA5vnN/v4PDqKyMR5lx7hZttPDgClv83E//FMNhR2TMcLUhfRUBHCmSl0oi9zMgDDqRUJkSxO3wm85+XLg==
+
+"@protobufjs/codegen@^2.0.4":
+  version "2.0.4"
+  resolved "https://registry.yarnpkg.com/@protobufjs/codegen/-/codegen-2.0.4.tgz#7ef37f0d010fb028ad1ad59722e506d9262815cb"
+  integrity sha512-YyFaikqM5sH0ziFZCN3xDC7zeGaB/d0IUb9CATugHWbd1FRFwWwt4ld4OYMPWu5a3Xe01mGAULCdqhMlPl29Jg==
+
+"@protobufjs/eventemitter@^1.1.0":
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/@protobufjs/eventemitter/-/eventemitter-1.1.0.tgz#355cbc98bafad5978f9ed095f397621f1d066b70"
+  integrity sha512-j9ednRT81vYJ9OfVuXG6ERSTdEL1xVsNgqpkxMsbIabzSo3goCjDIveeGv5d03om39ML71RdmrGNjG5SReBP/Q==
+
+"@protobufjs/fetch@^1.1.0":
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/@protobufjs/fetch/-/fetch-1.1.0.tgz#ba99fb598614af65700c1619ff06d454b0d84c45"
+  integrity sha512-lljVXpqXebpsijW71PZaCYeIcE5on1w5DlQy5WH6GLbFryLUrBD4932W/E2BSpfRJWseIL4v/KPgBFxDOIdKpQ==
+  dependencies:
+    "@protobufjs/aspromise" "^1.1.1"
+    "@protobufjs/inquire" "^1.1.0"
+
+"@protobufjs/float@^1.0.2":
+  version "1.0.2"
+  resolved "https://registry.yarnpkg.com/@protobufjs/float/-/float-1.0.2.tgz#5e9e1abdcb73fc0a7cb8b291df78c8cbd97b87d1"
+  integrity sha512-Ddb+kVXlXst9d+R9PfTIxh1EdNkgoRe5tOX6t01f1lYWOvJnSPDBlG241QLzcyPdoNTsblLUdujGSE4RzrTZGQ==
+
+"@protobufjs/inquire@^1.1.0":
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/@protobufjs/inquire/-/inquire-1.1.0.tgz#ff200e3e7cf2429e2dcafc1140828e8cc638f089"
+  integrity sha512-kdSefcPdruJiFMVSbn801t4vFK7KB/5gd2fYvrxhuJYg8ILrmn9SKSX2tZdV6V+ksulWqS7aXjBcRXl3wHoD9Q==
+
+"@protobufjs/path@^1.1.2":
+  version "1.1.2"
+  resolved "https://registry.yarnpkg.com/@protobufjs/path/-/path-1.1.2.tgz#6cc2b20c5c9ad6ad0dccfd21ca7673d8d7fbf68d"
+  integrity sha512-6JOcJ5Tm08dOHAbdR3GrvP+yUUfkjG5ePsHYczMFLq3ZmMkAD98cDgcT2iA1lJ9NVwFd4tH/iSSoe44YWkltEA==
+
+"@protobufjs/pool@^1.1.0":
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/@protobufjs/pool/-/pool-1.1.0.tgz#09fd15f2d6d3abfa9b65bc366506d6ad7846ff54"
+  integrity sha512-0kELaGSIDBKvcgS4zkjz1PeddatrjYcmMWOlAuAPwAeccUrPHdUqo/J6LiymHHEiJT5NrF1UVwxY14f+fy4WQw==
+
+"@protobufjs/utf8@^1.1.0":
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/@protobufjs/utf8/-/utf8-1.1.0.tgz#a777360b5b39a1a2e5106f8e858f2fd2d060c570"
+  integrity sha512-Vvn3zZrhQZkkBE8LSuW3em98c0FwgO4nxzv6OdSxPKJIEKY2bGbHn+mhGIPerzI4twdxaP8/0+06HBpwf345Lw==
+
 "@puppeteer/browsers@1.9.0":
   version "1.9.0"
   resolved "https://registry.yarnpkg.com/@puppeteer/browsers/-/browsers-1.9.0.tgz#dfd0aad0bdc039572f1b57648f189525d627b7ff"
@@ -107,6 +160,11 @@
   resolved "https://registry.yarnpkg.com/@tootallnate/quickjs-emscripten/-/quickjs-emscripten-0.23.0.tgz#db4ecfd499a9765ab24002c3b696d02e6d32a12c"
   integrity sha512-C5Mc6rdnsaJDjO3UpGW/CQTHtCKaYlScZTly4JIu97Jxo/odCiH0ITnDXSJPTOrEKk/ycSZ0AOgTmkDtkOsvIA==
 
+"@types/long@^4.0.1":
+  version "4.0.2"
+  resolved "https://registry.yarnpkg.com/@types/long/-/long-4.0.2.tgz#b74129719fc8d11c01868010082d483b7545591a"
+  integrity sha512-MqTGEo5bj5t157U6fA/BiDynNkn0YknVdh48CMPkTSpFTVmvao5UQmm7uEF6xBEo7qIMAlY/JSleYaE6VOdpaA==
+
 "@types/mailparser@^3.0.0":
   version "3.4.4"
   resolved "https://registry.yarnpkg.com/@types/mailparser/-/mailparser-3.4.4.tgz#0bd71e205573b9dd9a445e10a8b8cb0e45420998"
@@ -128,6 +186,13 @@
   resolved "https://registry.yarnpkg.com/@types/node/-/node-20.4.2.tgz#129cc9ae69f93824f92fac653eebfb4812ab4af9"
   integrity sha512-Dd0BYtWgnWJKwO1jkmTrzofjK2QXXcai0dmtzvIBhcA+RsG5h8R3xlyta0kGOZRNfL9GuRtb1knmPEhQrePCEw==
 
+"@types/node@>=13.7.0":
+  version "20.10.4"
+  resolved "https://registry.yarnpkg.com/@types/node/-/node-20.10.4.tgz#b246fd84d55d5b1b71bf51f964bd514409347198"
+  integrity sha512-D08YG6rr8X90YB56tSIuBaddy/UXAA9RKJoFvrsnogAum/0pmjkgi4+2nx96A330FmioegBWmEYQ+syqCFaveg==
+  dependencies:
+    undici-types "~5.26.4"
+
 "@types/node@^18.11.18":
   version "18.18.7"
   resolved "https://registry.yarnpkg.com/@types/node/-/node-18.18.7.tgz#bb3a7068dc4ba421b6968f2a259298b3a4e129e8"
@@ -152,6 +217,16 @@
   dependencies:
     "@types/node" "*"
 
+"@xenova/transformers@^2.11.0":
+  version "2.11.0"
+  resolved "https://registry.yarnpkg.com/@xenova/transformers/-/transformers-2.11.0.tgz#db9695240e5880823bee9199f27d7e51e7a09379"
+  integrity sha512-i/oaTbVJI+pbkWiUZydmaGFlSh3167N+gimkIJBlHf150wQWffwGE9dPttLsS9cLlmty95Z1MkVQmibl/j7bSg==
+  dependencies:
+    onnxruntime-web "1.14.0"
+    sharp "^0.32.0"
+  optionalDependencies:
+    onnxruntime-node "1.14.0"
+
 "@xmldom/xmldom@^0.8.10", "@xmldom/xmldom@^0.8.6":
   version "0.8.10"
   resolved "https://registry.yarnpkg.com/@xmldom/xmldom/-/xmldom-0.8.10.tgz#a1337ca426aa61cef9fe15b5b28e340a72f6fa99"
@@ -277,6 +352,11 @@ ast-types@^0.13.4:
   dependencies:
     tslib "^2.0.1"
 
+async@>=0.2.9:
+  version "3.2.5"
+  resolved "https://registry.yarnpkg.com/async/-/async-3.2.5.tgz#ebd52a8fdaf7a2289a24df399f8d8485c8a46b66"
+  integrity sha512-baNZyqaaLhyLVKm/DlvdW051MSgO6b8eVfIezl9E5PqWxFgzLm/wQntEW4zOytVburDEr0JlALEpdOFwvErLsg==
+
 asynckit@^0.4.0:
   version "0.4.0"
   resolved "https://registry.yarnpkg.com/asynckit/-/asynckit-0.4.0.tgz#c79ed97f7f34cb8f2ba1bc9790bcc366474b4b79"
@@ -338,6 +418,15 @@ bl@^1.0.0:
     readable-stream "^2.3.5"
     safe-buffer "^5.1.1"
 
+bl@^4.0.3:
+  version "4.1.0"
+  resolved "https://registry.yarnpkg.com/bl/-/bl-4.1.0.tgz#451535264182bec2fbbc83a62ab98cf11d9f7b3a"
+  integrity sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==
+  dependencies:
+    buffer "^5.5.0"
+    inherits "^2.0.4"
+    readable-stream "^3.4.0"
+
 bluebird@~3.4.0:
   version "3.4.7"
   resolved "https://registry.yarnpkg.com/bluebird/-/bluebird-3.4.7.tgz#f72d760be09b7f76d08ed8fae98b289a8d05fab3"
@@ -427,7 +516,7 @@ buffer-from@^1.0.0:
   resolved "https://registry.yarnpkg.com/buffer-from/-/buffer-from-1.1.2.tgz#2b146a6fd72e80b4f55d255f35ed59a3a9a41bd5"
   integrity sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==
 
-buffer@^5.2.1:
+buffer@^5.2.1, buffer@^5.5.0:
   version "5.7.1"
   resolved "https://registry.yarnpkg.com/buffer/-/buffer-5.7.1.tgz#ba62e7c13133053582197160851a8f648e99eed0"
   integrity sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==
@@ -494,6 +583,11 @@ chokidar@^3.5.2:
   optionalDependencies:
     fsevents "~2.3.2"
 
+chownr@^1.1.1:
+  version "1.1.4"
+  resolved "https://registry.yarnpkg.com/chownr/-/chownr-1.1.4.tgz#6fc9d7b42d32a583596337666e7d08084da2cc6b"
+  integrity sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==
+
 chownr@^2.0.0:
   version "2.0.0"
   resolved "https://registry.yarnpkg.com/chownr/-/chownr-2.0.0.tgz#15bfbe53d2eab4cf70f18a8cd68ebe5b3cb1dece"
@@ -535,16 +629,32 @@ color-name@1.1.3:
   resolved "https://registry.yarnpkg.com/color-name/-/color-name-1.1.3.tgz#a7d0558bd89c42f795dd42328f740831ca53bc25"
   integrity sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==
 
-color-name@~1.1.4:
+color-name@^1.0.0, color-name@~1.1.4:
   version "1.1.4"
   resolved "https://registry.yarnpkg.com/color-name/-/color-name-1.1.4.tgz#c2a09a87acbde69543de6f63fa3995c826c536a2"
   integrity sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==
 
+color-string@^1.9.0:
+  version "1.9.1"
+  resolved "https://registry.yarnpkg.com/color-string/-/color-string-1.9.1.tgz#4467f9146f036f855b764dfb5bf8582bf342c7a4"
+  integrity sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==
+  dependencies:
+    color-name "^1.0.0"
+    simple-swizzle "^0.2.2"
+
 color-support@^1.1.2:
   version "1.1.3"
   resolved "https://registry.yarnpkg.com/color-support/-/color-support-1.1.3.tgz#93834379a1cc9a0c61f82f52f0d04322251bd5a2"
   integrity sha512-qiBjkpbMLO/HL68y+lh4q0/O1MZFj2RX6X/KmMa3+gJD3z+WwI1ZzDHysvqHGS3mP6mznPckpXmw1nI9cJjyRg==
 
+color@^4.2.3:
+  version "4.2.3"
+  resolved "https://registry.yarnpkg.com/color/-/color-4.2.3.tgz#d781ecb5e57224ee43ea9627560107c0e0c6463a"
+  integrity sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==
+  dependencies:
+    color-convert "^2.0.1"
+    color-string "^1.9.0"
+
 combined-stream@^1.0.8:
   version "1.0.8"
   resolved "https://registry.yarnpkg.com/combined-stream/-/combined-stream-1.0.8.tgz#c3d45a8b34fd730631a110a8a2520682b31d5a7f"
@@ -670,6 +780,13 @@ decamelize@1.2.0:
   resolved "https://registry.yarnpkg.com/decamelize/-/decamelize-1.2.0.tgz#f6534d15148269b20352e7bee26f501f9a191290"
   integrity sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==
 
+decompress-response@^6.0.0:
+  version "6.0.0"
+  resolved "https://registry.yarnpkg.com/decompress-response/-/decompress-response-6.0.0.tgz#ca387612ddb7e104bd16d85aab00d5ecf09c66fc"
+  integrity sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==
+  dependencies:
+    mimic-response "^3.1.0"
+
 decompress-tar@^4.0.0, decompress-tar@^4.1.0, decompress-tar@^4.1.1:
   version "4.1.1"
   resolved "https://registry.yarnpkg.com/decompress-tar/-/decompress-tar-4.1.1.tgz#718cbd3fcb16209716e70a26b84e7ba4592e5af1"
@@ -723,6 +840,11 @@ decompress@^4.2.0:
     pify "^2.3.0"
     strip-dirs "^2.0.0"
 
+deep-extend@^0.6.0:
+  version "0.6.0"
+  resolved "https://registry.yarnpkg.com/deep-extend/-/deep-extend-0.6.0.tgz#c4fa7c95404a17a9c3e8ca7e1537312b736330ac"
+  integrity sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA==
+
 deepmerge@^4.3.1:
   version "4.3.1"
   resolved "https://registry.yarnpkg.com/deepmerge/-/deepmerge-4.3.1.tgz#44b5f2147cd3b00d4b56137685966f26fd25dd4a"
@@ -757,7 +879,7 @@ destroy@1.2.0:
   resolved "https://registry.yarnpkg.com/destroy/-/destroy-1.2.0.tgz#4803735509ad8be552934c67df614f94e66fa015"
   integrity sha512-2sJGJTaXIIaR1w4iJSNoN0hnMY7Gpc/n8D4qSCJw8QqFWXf7cuAgnEHxBpweaVcPevC2l3KpjYCx3NypQQgaJg==
 
-detect-libc@^2.0.0:
+detect-libc@^2.0.0, detect-libc@^2.0.2:
   version "2.0.2"
   resolved "https://registry.yarnpkg.com/detect-libc/-/detect-libc-2.0.2.tgz#8ccf2ba9315350e1241b88d0ac3b0e1fbd99605d"
   integrity sha512-UX6sGumvvqSaXgdKGUsgZWqcUyIXZ/vZTrlRT/iobiKhGL0zL4d3osHj3uqllWJK+i+sixDS/3COVEOFbupFyw==
@@ -849,7 +971,7 @@ encoding-japanese@2.0.0:
   resolved "https://registry.yarnpkg.com/encoding-japanese/-/encoding-japanese-2.0.0.tgz#fa0226e5469e7b5b69a04fea7d5481bd1fa56936"
   integrity sha512-++P0RhebUC8MJAwJOsT93dT+5oc5oPImp1HubZpAuCZ5kTLnhuuBhKHj2jJeO/Gj93idPBWmIuQ9QWMe5rX3pQ==
 
-end-of-stream@^1.0.0, end-of-stream@^1.1.0:
+end-of-stream@^1.0.0, end-of-stream@^1.1.0, end-of-stream@^1.4.1:
   version "1.4.4"
   resolved "https://registry.yarnpkg.com/end-of-stream/-/end-of-stream-1.4.4.tgz#5ae64a5f45057baf3626ec14da0ca5e4b2431eb0"
   integrity sha512-+uw1inIHVPQoaVuHzRyXd21icM+cnt4CzD5rW+NC1wjOUSTOs+Te7FOv7AhN7vS9x/oIyhLP5PR1H+phQAHu5Q==
@@ -924,6 +1046,11 @@ eventemitter3@^4.0.4:
   resolved "https://registry.yarnpkg.com/eventemitter3/-/eventemitter3-4.0.7.tgz#2de9b68f6528d5644ef5c59526a1b4a07306169f"
   integrity sha512-8guHBZCwKnFhYdHr2ysuRWErTwhoN2X8XELRlrRwpmfeY2jjuUN4taQMsULKUVo1K4DvZl+0pgfyoysHxvmvEw==
 
+expand-template@^2.0.3:
+  version "2.0.3"
+  resolved "https://registry.yarnpkg.com/expand-template/-/expand-template-2.0.3.tgz#6e14b3fcee0f3a6340ecb57d2e8918692052a47c"
+  integrity sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg==
+
 expr-eval@^2.0.2:
   version "2.0.2"
   resolved "https://registry.yarnpkg.com/expr-eval/-/expr-eval-2.0.2.tgz#fa6f044a7b0c93fde830954eb9c5b0f7fbc7e201"
@@ -1048,6 +1175,19 @@ flat@^5.0.2:
   resolved "https://registry.yarnpkg.com/flat/-/flat-5.0.2.tgz#8ca6fe332069ffa9d324c327198c598259ceb241"
   integrity sha512-b6suED+5/3rTpUBdG1gupIl8MPFCAMA0QXwmljLhvCUKcUvdE4gWky9zpuGCcXHOsz4J9wPGNWq6OKpmIzz3hQ==
 
+flatbuffers@^1.12.0:
+  version "1.12.0"
+  resolved "https://registry.yarnpkg.com/flatbuffers/-/flatbuffers-1.12.0.tgz#72e87d1726cb1b216e839ef02658aa87dcef68aa"
+  integrity sha512-c7CZADjRcl6j0PlvFy0ZqXQ67qSEZfrVPynmnL+2zPc+NtMvrF8Y0QceMo7QqnSPc7+uWjUIAbvCQ5WIKlMVdQ==
+
+fluent-ffmpeg@^2.1.2:
+  version "2.1.2"
+  resolved "https://registry.yarnpkg.com/fluent-ffmpeg/-/fluent-ffmpeg-2.1.2.tgz#c952de2240f812ebda0aa8006d7776ee2acf7d74"
+  integrity sha512-IZTB4kq5GK0DPp7sGQ0q/BWurGHffRtQQwVkiqDgeO6wYJLLV5ZhgNOQ65loZxxuPMKZKZcICCUnaGtlxBiR0Q==
+  dependencies:
+    async ">=0.2.9"
+    which "^1.1.1"
+
 form-data-encoder@1.7.2:
   version "1.7.2"
   resolved "https://registry.yarnpkg.com/form-data-encoder/-/form-data-encoder-1.7.2.tgz#1f1ae3dccf58ed4690b86d87e4f57c654fbab040"
@@ -1189,6 +1329,11 @@ get-uri@^6.0.1:
     debug "^4.3.4"
     fs-extra "^8.1.0"
 
+github-from-package@0.0.0:
+  version "0.0.0"
+  resolved "https://registry.yarnpkg.com/github-from-package/-/github-from-package-0.0.0.tgz#97fb5d96bfde8973313f20e8288ef9a167fa64ce"
+  integrity sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw==
+
 glob-parent@~5.1.2:
   version "5.1.2"
   resolved "https://registry.yarnpkg.com/glob-parent/-/glob-parent-5.1.2.tgz#869832c58034fe68a4093c17dc15e8340d8401c4"
@@ -1256,6 +1401,11 @@ gtoken@^6.1.0:
     google-p12-pem "^4.0.0"
     jws "^4.0.0"
 
+guid-typescript@^1.0.9:
+  version "1.0.9"
+  resolved "https://registry.yarnpkg.com/guid-typescript/-/guid-typescript-1.0.9.tgz#e35f77003535b0297ea08548f5ace6adb1480ddc"
+  integrity sha512-Y8T4vYhEfwJOTbouREvG+3XDsjr8E3kIr7uf+JZ0BYloFsttiHU0WfvANVsR7TxNUJa/WpCnw/Ino/p+DeBhBQ==
+
 has-flag@^3.0.0:
   version "3.0.0"
   resolved "https://registry.yarnpkg.com/has-flag/-/has-flag-3.0.0.tgz#b5d454dc2199ae225699f3467e5a07f3b955bafd"
@@ -1401,11 +1551,16 @@ inflight@^1.0.4:
     once "^1.3.0"
     wrappy "1"
 
-inherits@2, inherits@2.0.4, inherits@^2.0.3, inherits@~2.0.3:
+inherits@2, inherits@2.0.4, inherits@^2.0.3, inherits@^2.0.4, inherits@~2.0.3:
   version "2.0.4"
   resolved "https://registry.yarnpkg.com/inherits/-/inherits-2.0.4.tgz#0fa2c64f932917c3433a0ded55363aae37416b7c"
   integrity sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==
 
+ini@~1.3.0:
+  version "1.3.8"
+  resolved "https://registry.yarnpkg.com/ini/-/ini-1.3.8.tgz#a29da425b48806f34767a4efce397269af28432c"
+  integrity sha512-JV/yugV2uzW5iMRSiZAyDtQd+nxtUnjeLt0acNdw98kKLrvuRVyB80tsREOE7yvGVgalhZ6RNXCmEHkUKBKxew==
+
 ip@^1.1.8:
   version "1.1.8"
   resolved "https://registry.yarnpkg.com/ip/-/ip-1.1.8.tgz#ae05948f6b075435ed3307acce04629da8cdbf48"
@@ -1431,6 +1586,11 @@ is-arrayish@^0.2.1:
   resolved "https://registry.yarnpkg.com/is-arrayish/-/is-arrayish-0.2.1.tgz#77c99840527aa8ecb1a8ba697b80645a7a926a9d"
   integrity sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg==
 
+is-arrayish@^0.3.1:
+  version "0.3.2"
+  resolved "https://registry.yarnpkg.com/is-arrayish/-/is-arrayish-0.3.2.tgz#4574a2ae56f7ab206896fb431eaeed066fdf8f03"
+  integrity sha512-eVRqCvVlZbuw3GrM63ovNSNAeA1K16kaR/LRY/92w0zxQ5/1YzwblUX652i4Xs9RwAGjW9d9y6X88t8OaAJfWQ==
+
 is-binary-path@~2.1.0:
   version "2.1.0"
   resolved "https://registry.yarnpkg.com/is-binary-path/-/is-binary-path-2.1.0.tgz#ea1f7f3b80f064236e83470f86c09c254fb45b09"
@@ -1485,6 +1645,11 @@ isarray@~1.0.0:
   resolved "https://registry.yarnpkg.com/isarray/-/isarray-1.0.0.tgz#bb935d48582cba168c06834957a54a3e07124f11"
   integrity sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==
 
+isexe@^2.0.0:
+  version "2.0.0"
+  resolved "https://registry.yarnpkg.com/isexe/-/isexe-2.0.0.tgz#e8fbf374dc556ff8947a10dcb0572d633f2cfa10"
+  integrity sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==
+
 js-tiktoken@^1.0.7:
   version "1.0.7"
   resolved "https://registry.yarnpkg.com/js-tiktoken/-/js-tiktoken-1.0.7.tgz#56933fcd2093e8304060dfde3071bda91812e6f5"
@@ -1667,6 +1832,11 @@ linkify-it@4.0.1:
   dependencies:
     uc.micro "^1.0.1"
 
+long@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/long/-/long-4.0.0.tgz#9a7b71cfb7d361a194ea555241c92f7468d5bf28"
+  integrity sha512-XsP+KhQif4bjX1kbuSiySJFNAehNxgLb6hPRGJ9QsUr8ajHkuXGdrHmFUTUUXhDwVX2R5bY4JNZEwbUiMhV+MA==
+
 lop@^0.4.1:
   version "0.4.1"
   resolved "https://registry.yarnpkg.com/lop/-/lop-0.4.1.tgz#744f1696ef480e68ce1947fe557b09db5af2a738"
@@ -1797,6 +1967,11 @@ mime@^3.0.0:
   resolved "https://registry.yarnpkg.com/mime/-/mime-3.0.0.tgz#b374550dca3a0c18443b0c950a6a58f1931cf7a7"
   integrity sha512-jSCU7/VB1loIWBZe14aEYHU/+1UMEHoaO7qxCOVJOw9GgH72VAWppxNcjU+x9a2k3GSIBXNKxXQFqRvvZ7vr3A==
 
+mimic-response@^3.1.0:
+  version "3.1.0"
+  resolved "https://registry.yarnpkg.com/mimic-response/-/mimic-response-3.1.0.tgz#2d1d59af9c1b129815accc2c46a022a5ce1fa3c9"
+  integrity sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==
+
 minimatch@^3.1.1, minimatch@^3.1.2:
   version "3.1.2"
   resolved "https://registry.yarnpkg.com/minimatch/-/minimatch-3.1.2.tgz#19cd194bfd3e428f049a70817c038d89ab4be35b"
@@ -1804,7 +1979,7 @@ minimatch@^3.1.1, minimatch@^3.1.2:
   dependencies:
     brace-expansion "^1.1.7"
 
-minimist@^1.2.6:
+minimist@^1.2.0, minimist@^1.2.3, minimist@^1.2.6:
   version "1.2.8"
   resolved "https://registry.yarnpkg.com/minimist/-/minimist-1.2.8.tgz#c1a464e7693302e082a075cee0c057741ac4772c"
   integrity sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==
@@ -1834,7 +2009,7 @@ mitt@3.0.1:
   resolved "https://registry.yarnpkg.com/mitt/-/mitt-3.0.1.tgz#ea36cf0cc30403601ae074c8f77b7092cdab36d1"
   integrity sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==
 
-mkdirp-classic@^0.5.2:
+mkdirp-classic@^0.5.2, mkdirp-classic@^0.5.3:
   version "0.5.3"
   resolved "https://registry.yarnpkg.com/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz#fa10c9115cc6d8865be221ba47ee9bed78601113"
   integrity sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==
@@ -1920,6 +2095,11 @@ multer@^1.4.5-lts.1:
     type-is "^1.6.4"
     xtend "^4.0.0"
 
+napi-build-utils@^1.0.1:
+  version "1.0.2"
+  resolved "https://registry.yarnpkg.com/napi-build-utils/-/napi-build-utils-1.0.2.tgz#b1fddc0b2c46e380a0b7a76f984dd47c41a13806"
+  integrity sha512-ONmRUqK7zj7DWX0D9ADe03wbwOBZxNAfF20PlGfCWQcD3+/MakShIHrMqx9YwPTfxDdF1zLeL+RGZiR9kGMLdg==
+
 negotiator@0.6.3:
   version "0.6.3"
   resolved "https://registry.yarnpkg.com/negotiator/-/negotiator-0.6.3.tgz#58e323a72fedc0d6f9cd4d31fe49f51479590ccd"
@@ -1930,11 +2110,23 @@ netmask@^2.0.2:
   resolved "https://registry.yarnpkg.com/netmask/-/netmask-2.0.2.tgz#8b01a07644065d536383835823bc52004ebac5e7"
   integrity sha512-dBpDMdxv9Irdq66304OLfEmQ9tbNRFnFTuZiLo+bD+r332bBmMJ8GBLXklIXXgxd3+v9+KUnZaUR5PJMa75Gsg==
 
+node-abi@^3.3.0:
+  version "3.52.0"
+  resolved "https://registry.yarnpkg.com/node-abi/-/node-abi-3.52.0.tgz#ffba0a85f54e552547e5849015f40f9514d5ba7c"
+  integrity sha512-JJ98b02z16ILv7859irtXn4oUaFWADtvkzy2c0IAatNVX2Mc9Yoh8z6hZInn3QwvMEYhHuQloYi+TTQy67SIdQ==
+  dependencies:
+    semver "^7.3.5"
+
 node-addon-api@^5.0.0:
   version "5.1.0"
   resolved "https://registry.yarnpkg.com/node-addon-api/-/node-addon-api-5.1.0.tgz#49da1ca055e109a23d537e9de43c09cca21eb762"
   integrity sha512-eh0GgfEkpnoWDq+VY8OyvYhFEzBk6jIYbRKdIlyTiAXIVJ8PyBaKb0rp7oDtoddbdoHWhq8wwr+XZ81F1rpNdA==
 
+node-addon-api@^6.1.0:
+  version "6.1.0"
+  resolved "https://registry.yarnpkg.com/node-addon-api/-/node-addon-api-6.1.0.tgz#ac8470034e58e67d0c6f1204a18ae6995d9c0d76"
+  integrity sha512-+eawOlIgy680F0kBzPUNFhMZGtJ1YmqM6l4+Crf4IkImjYrO/mqPwRMh352g23uIaQKFItcQ64I7KMaJxHgAVA==
+
 node-domexception@1.0.0:
   version "1.0.0"
   resolved "https://registry.yarnpkg.com/node-domexception/-/node-domexception-1.0.0.tgz#6888db46a1f71c0b76b3f7555016b63fe64766e5"
@@ -2054,6 +2246,37 @@ once@^1.3.0, once@^1.3.1, once@^1.4.0:
   dependencies:
     wrappy "1"
 
+onnx-proto@^4.0.4:
+  version "4.0.4"
+  resolved "https://registry.yarnpkg.com/onnx-proto/-/onnx-proto-4.0.4.tgz#2431a25bee25148e915906dda0687aafe3b9e044"
+  integrity sha512-aldMOB3HRoo6q/phyB6QRQxSt895HNNw82BNyZ2CMh4bjeKv7g/c+VpAFtJuEMVfYLMbRx61hbuqnKceLeDcDA==
+  dependencies:
+    protobufjs "^6.8.8"
+
+onnxruntime-common@~1.14.0:
+  version "1.14.0"
+  resolved "https://registry.yarnpkg.com/onnxruntime-common/-/onnxruntime-common-1.14.0.tgz#2bb5dac5261269779aa5fb6536ca379657de8bf6"
+  integrity sha512-3LJpegM2iMNRX2wUmtYfeX/ytfOzNwAWKSq1HbRrKc9+uqG/FsEA0bbKZl1btQeZaXhC26l44NWpNUeXPII7Ew==
+
+onnxruntime-node@1.14.0:
+  version "1.14.0"
+  resolved "https://registry.yarnpkg.com/onnxruntime-node/-/onnxruntime-node-1.14.0.tgz#c4ae6c355cfae7d83abaf36dd39a905c4a010217"
+  integrity sha512-5ba7TWomIV/9b6NH/1x/8QEeowsb+jBEvFzU6z0T4mNsFwdPqXeFUM7uxC6QeSRkEbWu3qEB0VMjrvzN/0S9+w==
+  dependencies:
+    onnxruntime-common "~1.14.0"
+
+onnxruntime-web@1.14.0:
+  version "1.14.0"
+  resolved "https://registry.yarnpkg.com/onnxruntime-web/-/onnxruntime-web-1.14.0.tgz#c8cee538781b1d4c1c6b043934f4a3e6ddf1466e"
+  integrity sha512-Kcqf43UMfW8mCydVGcX9OMXI2VN17c0p6XvR7IPSZzBf/6lteBzXHvcEVWDPmCKuGombl997HgLqj91F11DzXw==
+  dependencies:
+    flatbuffers "^1.12.0"
+    guid-typescript "^1.0.9"
+    long "^4.0.0"
+    onnx-proto "^4.0.4"
+    onnxruntime-common "~1.14.0"
+    platform "^1.3.6"
+
 openai@^4.19.0:
   version "4.20.1"
   resolved "https://registry.yarnpkg.com/openai/-/openai-4.20.1.tgz#afa0d496d125b5a0f6cebcb4b9aeabf71e00214e"
@@ -2230,6 +2453,29 @@ pinkie@^2.0.0:
   resolved "https://registry.yarnpkg.com/pinkie/-/pinkie-2.0.4.tgz#72556b80cfa0d48a974e80e77248e80ed4f7f870"
   integrity sha512-MnUuEycAemtSaeFSjXKW/aroV7akBbY+Sv+RkyqFjgAe73F+MR0TBWKBRDkmfWq/HiFmdavfZ1G7h4SPZXaCSg==
 
+platform@^1.3.6:
+  version "1.3.6"
+  resolved "https://registry.yarnpkg.com/platform/-/platform-1.3.6.tgz#48b4ce983164b209c2d45a107adb31f473a6e7a7"
+  integrity sha512-fnWVljUchTro6RiCFvCXBbNhJc2NijN7oIQxbwsyL0buWJPG85v81ehlHI9fXrJsMNgTofEoWIQeClKpgxFLrg==
+
+prebuild-install@^7.1.1:
+  version "7.1.1"
+  resolved "https://registry.yarnpkg.com/prebuild-install/-/prebuild-install-7.1.1.tgz#de97d5b34a70a0c81334fd24641f2a1702352e45"
+  integrity sha512-jAXscXWMcCK8GgCoHOfIr0ODh5ai8mj63L2nWrjuAgXE6tDyYGnx4/8o/rCgU+B4JSyZBKbeZqzhtwtC3ovxjw==
+  dependencies:
+    detect-libc "^2.0.0"
+    expand-template "^2.0.3"
+    github-from-package "0.0.0"
+    minimist "^1.2.3"
+    mkdirp-classic "^0.5.3"
+    napi-build-utils "^1.0.1"
+    node-abi "^3.3.0"
+    pump "^3.0.0"
+    rc "^1.2.7"
+    simple-get "^4.0.0"
+    tar-fs "^2.0.0"
+    tunnel-agent "^0.6.0"
+
 prettier@^2.4.1:
   version "2.8.8"
   resolved "https://registry.yarnpkg.com/prettier/-/prettier-2.8.8.tgz#e8c5d7e98a4305ffe3de2e1fc4aca1a71c28b1da"
@@ -2245,6 +2491,25 @@ progress@2.0.3:
   resolved "https://registry.yarnpkg.com/progress/-/progress-2.0.3.tgz#7e8cf8d8f5b8f239c1bc68beb4eb78567d572ef8"
   integrity sha512-7PiHtLll5LdnKIMw100I+8xJXR5gW2QwWYkT6iJva0bXitZKa/XMrSbdmg3r2Xnaidz9Qumd0VPaMrZlF9V9sA==
 
+protobufjs@^6.8.8:
+  version "6.11.4"
+  resolved "https://registry.yarnpkg.com/protobufjs/-/protobufjs-6.11.4.tgz#29a412c38bf70d89e537b6d02d904a6f448173aa"
+  integrity sha512-5kQWPaJHi1WoCpjTGszzQ32PG2F4+wRY6BmAT4Vfw56Q2FZ4YZzK20xUYQH4YkfehY1e6QSICrJquM6xXZNcrw==
+  dependencies:
+    "@protobufjs/aspromise" "^1.1.2"
+    "@protobufjs/base64" "^1.1.2"
+    "@protobufjs/codegen" "^2.0.4"
+    "@protobufjs/eventemitter" "^1.1.0"
+    "@protobufjs/fetch" "^1.1.0"
+    "@protobufjs/float" "^1.0.2"
+    "@protobufjs/inquire" "^1.1.0"
+    "@protobufjs/path" "^1.1.2"
+    "@protobufjs/pool" "^1.1.0"
+    "@protobufjs/utf8" "^1.1.0"
+    "@types/long" "^4.0.1"
+    "@types/node" ">=13.7.0"
+    long "^4.0.0"
+
 proxy-addr@~2.0.7:
   version "2.0.7"
   resolved "https://registry.yarnpkg.com/proxy-addr/-/proxy-addr-2.0.7.tgz#f19fe69ceab311eeb94b42e70e8c2070f9ba1025"
@@ -2350,6 +2615,16 @@ raw-body@2.5.2:
     iconv-lite "0.4.24"
     unpipe "1.0.0"
 
+rc@^1.2.7:
+  version "1.2.8"
+  resolved "https://registry.yarnpkg.com/rc/-/rc-1.2.8.tgz#cd924bf5200a075b83c188cd6b9e211b7fc0d3ed"
+  integrity sha512-y3bGgqKj3QBdxLbLkomlohkvsA8gdAiUQlSBJnBhfn+BPxg4bc62d8TcBW15wavDfgexCgccckhcZvywyQYPOw==
+  dependencies:
+    deep-extend "^0.6.0"
+    ini "~1.3.0"
+    minimist "^1.2.0"
+    strip-json-comments "~2.0.1"
+
 readable-stream@^2.2.2, readable-stream@^2.3.0, readable-stream@^2.3.5, readable-stream@~2.3.6:
   version "2.3.8"
   resolved "https://registry.yarnpkg.com/readable-stream/-/readable-stream-2.3.8.tgz#91125e8042bba1b9887f49345f6277027ce8be9b"
@@ -2363,7 +2638,7 @@ readable-stream@^2.2.2, readable-stream@^2.3.0, readable-stream@^2.3.5, readable
     string_decoder "~1.1.1"
     util-deprecate "~1.0.1"
 
-readable-stream@^3.6.0:
+readable-stream@^3.1.1, readable-stream@^3.4.0, readable-stream@^3.6.0:
   version "3.6.2"
   resolved "https://registry.yarnpkg.com/readable-stream/-/readable-stream-3.6.2.tgz#56a9b36ea965c00c5a93ef31eb111a0f11056967"
   integrity sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA==
@@ -2454,7 +2729,7 @@ semver@^6.0.0:
   resolved "https://registry.yarnpkg.com/semver/-/semver-6.3.1.tgz#556d2ef8689146e46dcea4bfdd095f3434dffcb4"
   integrity sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA==
 
-semver@^7.3.5:
+semver@^7.3.5, semver@^7.5.4:
   version "7.5.4"
   resolved "https://registry.yarnpkg.com/semver/-/semver-7.5.4.tgz#483986ec4ed38e1c6c48c34894a9182dbff68a6e"
   integrity sha512-1bCSESV6Pv+i21Hvpxp3Dx+pSD8lIPt8uVjRrxAUt/nbswYc+tK6Y2btiULjd4+fnq15PX+nqQDC7Oft7WkwcA==
@@ -2510,6 +2785,20 @@ setprototypeof@1.2.0:
   resolved "https://registry.yarnpkg.com/setprototypeof/-/setprototypeof-1.2.0.tgz#66c9a24a73f9fc28cbe66b09fed3d33dcaf1b424"
   integrity sha512-E5LDX7Wrp85Kil5bhZv46j8jOeboKq5JMmYM3gVGdGH8xFpPWXUMsNrlODCrkoxMEeNi/XZIwuRvY4XNwYMJpw==
 
+sharp@^0.32.0:
+  version "0.32.6"
+  resolved "https://registry.yarnpkg.com/sharp/-/sharp-0.32.6.tgz#6ad30c0b7cd910df65d5f355f774aa4fce45732a"
+  integrity sha512-KyLTWwgcR9Oe4d9HwCwNM2l7+J0dUQwn/yf7S0EnTtb0eVS4RxO0eUSvxPtzT4F3SY+C4K6fqdv/DO27sJ/v/w==
+  dependencies:
+    color "^4.2.3"
+    detect-libc "^2.0.2"
+    node-addon-api "^6.1.0"
+    prebuild-install "^7.1.1"
+    semver "^7.5.4"
+    simple-get "^4.0.1"
+    tar-fs "^3.0.4"
+    tunnel-agent "^0.6.0"
+
 side-channel@^1.0.4:
   version "1.0.4"
   resolved "https://registry.yarnpkg.com/side-channel/-/side-channel-1.0.4.tgz#efce5c8fdc104ee751b25c58d4290011fa5ea2cf"
@@ -2524,6 +2813,27 @@ signal-exit@^3.0.0:
   resolved "https://registry.yarnpkg.com/signal-exit/-/signal-exit-3.0.7.tgz#a9a1767f8af84155114eaabd73f99273c8f59ad9"
   integrity sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==
 
+simple-concat@^1.0.0:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/simple-concat/-/simple-concat-1.0.1.tgz#f46976082ba35c2263f1c8ab5edfe26c41c9552f"
+  integrity sha512-cSFtAPtRhljv69IK0hTVZQ+OfE9nePi/rtJmw5UjHeVyVroEqJXP1sFztKUy1qU+xvz3u/sfYJLa947b7nAN2Q==
+
+simple-get@^4.0.0, simple-get@^4.0.1:
+  version "4.0.1"
+  resolved "https://registry.yarnpkg.com/simple-get/-/simple-get-4.0.1.tgz#4a39db549287c979d352112fa03fd99fd6bc3543"
+  integrity sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==
+  dependencies:
+    decompress-response "^6.0.0"
+    once "^1.3.1"
+    simple-concat "^1.0.0"
+
+simple-swizzle@^0.2.2:
+  version "0.2.2"
+  resolved "https://registry.yarnpkg.com/simple-swizzle/-/simple-swizzle-0.2.2.tgz#a4da6b635ffcccca33f70d17cb92592de95e557a"
+  integrity sha512-JA//kQgZtbuY83m+xT+tXJkmJncGMTFT+C+g2h2R9uxkYIrE2yy9sgmcLhCnw57/WSD+Eh3J97FPEDFnbXnDUg==
+  dependencies:
+    is-arrayish "^0.3.1"
+
 simple-update-notifier@^1.0.7:
   version "1.1.0"
   resolved "https://registry.yarnpkg.com/simple-update-notifier/-/simple-update-notifier-1.1.0.tgz#67694c121de354af592b347cdba798463ed49c82"
@@ -2623,6 +2933,11 @@ strip-dirs@^2.0.0:
   dependencies:
     is-natural-number "^4.0.1"
 
+strip-json-comments@~2.0.1:
+  version "2.0.1"
+  resolved "https://registry.yarnpkg.com/strip-json-comments/-/strip-json-comments-2.0.1.tgz#3c531942e908c2697c0ec344858c286c7ca0a60a"
+  integrity sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ==
+
 strtok3@^6.2.4:
   version "6.3.0"
   resolved "https://registry.yarnpkg.com/strtok3/-/strtok3-6.3.0.tgz#358b80ffe6d5d5620e19a073aa78ce947a90f9a0"
@@ -2638,7 +2953,7 @@ supports-color@^5.3.0, supports-color@^5.5.0:
   dependencies:
     has-flag "^3.0.0"
 
-tar-fs@3.0.4:
+tar-fs@3.0.4, tar-fs@^3.0.4:
   version "3.0.4"
   resolved "https://registry.yarnpkg.com/tar-fs/-/tar-fs-3.0.4.tgz#a21dc60a2d5d9f55e0089ccd78124f1d3771dbbf"
   integrity sha512-5AFQU8b9qLfZCX9zp2duONhPmZv0hGYiBPJsyUdqMjzq/mqVpy/rEUSeHk1+YitmxugaptgBh5oDGU3VsAJq4w==
@@ -2647,6 +2962,16 @@ tar-fs@3.0.4:
     pump "^3.0.0"
     tar-stream "^3.1.5"
 
+tar-fs@^2.0.0:
+  version "2.1.1"
+  resolved "https://registry.yarnpkg.com/tar-fs/-/tar-fs-2.1.1.tgz#489a15ab85f1f0befabb370b7de4f9eb5cbe8784"
+  integrity sha512-V0r2Y9scmbDRLCNex/+hYzvp/zyYjvFbHPNgVTKfQvVrb6guiE/fxP+XblDNR011utopbkex2nM4dHNV6GDsng==
+  dependencies:
+    chownr "^1.1.1"
+    mkdirp-classic "^0.5.2"
+    pump "^3.0.0"
+    tar-stream "^2.1.4"
+
 tar-stream@^1.5.2:
   version "1.6.2"
   resolved "https://registry.yarnpkg.com/tar-stream/-/tar-stream-1.6.2.tgz#8ea55dab37972253d9a9af90fdcd559ae435c555"
@@ -2660,6 +2985,17 @@ tar-stream@^1.5.2:
     to-buffer "^1.1.1"
     xtend "^4.0.0"
 
+tar-stream@^2.1.4:
+  version "2.2.0"
+  resolved "https://registry.yarnpkg.com/tar-stream/-/tar-stream-2.2.0.tgz#acad84c284136b060dc3faa64474aa9aebd77287"
+  integrity sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==
+  dependencies:
+    bl "^4.0.3"
+    end-of-stream "^1.4.1"
+    fs-constants "^1.0.0"
+    inherits "^2.0.3"
+    readable-stream "^3.1.1"
+
 tar-stream@^3.1.5:
   version "3.1.6"
   resolved "https://registry.yarnpkg.com/tar-stream/-/tar-stream-3.1.6.tgz#6520607b55a06f4a2e2e04db360ba7d338cc5bab"
@@ -2733,6 +3069,13 @@ tslib@^2.0.1:
   resolved "https://registry.yarnpkg.com/tslib/-/tslib-2.6.2.tgz#703ac29425e7b37cd6fd456e92404d46d1f3e4ae"
   integrity sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q==
 
+tunnel-agent@^0.6.0:
+  version "0.6.0"
+  resolved "https://registry.yarnpkg.com/tunnel-agent/-/tunnel-agent-0.6.0.tgz#27a5dea06b36b04a0a9966774b290868f0fc40fd"
+  integrity sha512-McnNiV1l8RYeY8tBgEpuodCC1mLUdbSN+CYBL7kJsJNInOP8UjDDEwdk6Mw60vdLLrr5NHKZhMAOSrR2NZuQ+w==
+  dependencies:
+    safe-buffer "^5.0.1"
+
 type-is@^1.6.4, type-is@~1.6.18:
   version "1.6.18"
   resolved "https://registry.yarnpkg.com/type-is/-/type-is-1.6.18.tgz#4e552cd05df09467dcbc4ef739de89f2cf37c131"
@@ -2814,6 +3157,11 @@ vary@^1, vary@~1.1.2:
   resolved "https://registry.yarnpkg.com/vary/-/vary-1.1.2.tgz#2299f02c6ded30d4a5961b0b9f74524a18f634fc"
   integrity sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg==
 
+wavefile@^11.0.0:
+  version "11.0.0"
+  resolved "https://registry.yarnpkg.com/wavefile/-/wavefile-11.0.0.tgz#9302165874327ff63a704d00b154c753eaa1b8e7"
+  integrity sha512-/OBiAALgWU24IG7sC84cDO/KfFuvajWc5Uec0oV2zrpOOZZDgGdOwHwgEzOrwh8jkubBk7PtZfQBIcI1OaE5Ng==
+
 web-streams-polyfill@4.0.0-beta.3:
   version "4.0.0-beta.3"
   resolved "https://registry.yarnpkg.com/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz#2898486b74f5156095e473efe989dcf185047a38"
@@ -2837,6 +3185,13 @@ whatwg-url@^5.0.0:
     tr46 "~0.0.3"
     webidl-conversions "^3.0.0"
 
+which@^1.1.1:
+  version "1.3.1"
+  resolved "https://registry.yarnpkg.com/which/-/which-1.3.1.tgz#a45043d54f5805316da8d62f9f50918d3da70b0a"
+  integrity sha512-HxJdYWq1MTIQbJ3nw0cqssHoTNU267KlrDuGZ1WYlxDStUtKUhOaJmh112/TZmHxxUfuJqPXSOm7tDyas0OSIQ==
+  dependencies:
+    isexe "^2.0.0"
+
 wide-align@^1.1.2:
   version "1.1.5"
   resolved "https://registry.yarnpkg.com/wide-align/-/wide-align-1.1.5.tgz#df1d4c206854369ecf3c9a4898f1b23fbd9d15d3"
diff --git a/frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx b/frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx
index dccd598a..a6cee8c8 100644
--- a/frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx
+++ b/frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx
@@ -1,5 +1,5 @@
 import { CloudArrowUp } from "@phosphor-icons/react";
-import { useCallback, useEffect, useState } from "react";
+import { useEffect, useState } from "react";
 import showToast from "../../../../../utils/toast";
 import System from "../../../../../models/system";
 import { useDropzone } from "react-dropzone";
@@ -109,7 +109,6 @@ export default function UploadFile({
               Click to upload or drag and drop
             </div>
             <div className="text-white text-opacity-60 text-xs font-medium py-1">
-              Supported file extensions are{" "}
               {Object.values(fileTypes ?? [])
                 .flat()
                 .join(" ")}
diff --git a/server/storage/models/README.md b/server/storage/models/README.md
index 1a63484c..965083dc 100644
--- a/server/storage/models/README.md
+++ b/server/storage/models/README.md
@@ -9,6 +9,11 @@ When your embedding engine preference is `native` we will use the ONNX **all-Min
 
 If you are using the `native` embedding engine your vector database should be configured to accept 384-dimension models if that parameter is directly editable (Pinecone only).
 
+## Audio/Video transcription
+AnythingLLM allows you to upload various audio and video formats as source documents. In all cases the audio tracks will be transcribed by a locally running ONNX model **whisper-small** built by [Xenova on HuggingFace.co](https://huggingface.co/Xenova/whisper-small). The model is a smaller version of the OpenAI Whisper model. Given the model runs locally on CPU, larger files will result in longer transcription times.
+
+Once transcribed you can embed these transcriptions into your workspace like you would any other file! 
+
 ## Text generation (LLM selection)
 > [!IMPORTANT]
 > Use of a locally running LLM model is **experimental** and may behave unexpectedly, crash, or not function at all.