Initial release

.github/workflows/ci-cd.yaml

@@ -0,0 +1,33 @@
+# Copyright Jiaqi Liu
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+---
+name: CI/CD
+
+on:
+  pull_request:
+  push:
+    branches: [master]
+
+jobs:
+  sync-to-huggingface-space:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        run: git push https://QubitPi:$HF_TOKEN@huggingface.co/spaces/QubitPi/tiger master:main -f
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}

.gitignore

@@ -0,0 +1,4 @@
+.venv
+.idea/
+.DS_Store
+__pycache__

.streamlit/config.toml

@@ -0,0 +1,8 @@
+[theme]
+primaryColor="#F63366"
+backgroundColor="#FFFFFF"
+secondaryBackgroundColor="#F0F2F6"
+textColor="#262730"
+font="sans serif"
+[server]
+maxUploadSize=1028

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Jiaqi Liu
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,80 @@
+---
+title: Tiger
+emoji: 🎥
+colorFrom: blue
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.39.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+short_description: Movie transcription for language learners
+---
+
+[![Hugging Face space badge]][Hugging Face space URL]
+[![Hugging Face sync status badge]][Hugging Face sync status URL]
+[![Apache License Badge]][Apache License, Version 2.0]
+
+Tiger
+=====
+
+__Tiger__ is an automatic speech recognition application that takes a video file as input and generates a video with
+subtitles as well as downloadable .txt, .vtt, .srt transcription files. Tiger generates transcriptions using the
+[OpenAI Whisper](https://openai.com/blog/whisper) models.
+
+The app is available on [Hugging Face space][Project Tiger on Hugging Face]. Please check it out.
+
+How Project Tiger Started
+-------------------------
+
+I don't believe NLP is inherently AI. [Project Tiger](), however, enlightened me on what way should AI makes NLP more
+powerful for people.
+
+Paraphrasing movie lines has been my favorite approach to learn a foreign language. This was why I was able to speak
+close-native English in early days. I used this same tactic for German today as well.
+
+One morning I was studying German with the famous German WW2 movie
+[_Generation War_](https://youtu.be/TmyGPX23px4?si=wk3V62vLUe9zFzfo). Managing to find its subtitles[^1][^2][^3] were
+easy for me. A problem, however, soon arose as I proceeded with them: _the subtitles had errors - missing couple of
+phrases every few other lines_. This was a big NO for language learners like me. In old days 10 years ago, I would've
+reached a dead end... 
+
+[^1]: https://www.opensubtitles.org/en/subtitles/6243166/generation-war-eine-andere-zeit-de
+[^2]: https://www.opensubtitles.org/en/subtitles/6243167/generation-war-ein-anderer-krieg-de
+[^3]: https://www.opensubtitles.org/en/subtitles/6243168/generation-war-ein-anderes-land-de
+
+Almost immediately, however, I had this idea of having AI figure out those missing words for me; so I tried
+[OpenAI's Whisper](https://huggingface.co/spaces/openai/whisper) which, quite surprisingly, yield 100% accurate results.
+That was the first occasion where AI produced significant solid values for my life as a language learner.
+
+Being so excited, I decided to industrialize this process and hereby present it as [Project Tiger on Hugging Face], an
+__AI movie transcription service that targets specifically for language learners__
+
+> [!NOTE]
+> 
+> On name "__Tiger__"
+>
+> The project name _tiger_ was taken from the _German heavy tank of World War II -
+> [Tiger I](https://tanks-encyclopedia.com/ww2/germany/panzer-vi_tiger.php#index17)_.
+> 
+> I chose this name because the project idea was spawned from the study of German language. More importantly, _Tiger I_
+> has been widely recognized as a revolutionary tank being a crown jewels in the history of warfare technology: 
+> 
+> > _"It is tempting to view the appearance of the Tiger tank as revolutionary, ... the end result was a machine that
+> > represented a quantum leap forward in tank design and changed everything - forever"_[^4]
+> 
+> As _Tiger_ had steered the direction of next-generation heavy tank, this project has also revolutionized my view
+> toward AI subconsciously and serves as an empirical guide on how I should make NLP more powerful for people with AI.
+
+[^4]: _[Tiger tank : Panzerkampfwagen VI Tiger I Ausf. E (SdKfz 181): owner's workshop manual](https://a.co/d/28OzPsK)_, The Tank Museum, 2011. p.13
+
+[Apache License Badge]: https://img.shields.io/badge/Apache%202.0-F25910.svg?style=for-the-badge&logo=Apache&logoColor=white
+[Apache License, Version 2.0]: https://www.apache.org/licenses/LICENSE-2.0
+
+[Hugging Face space badge]: https://img.shields.io/badge/Hugging%20Face%20Space-tiger-FFD21E?style=for-the-badge&logo=huggingface&logoColor=white
+[Hugging Face space URL]: https://huggingface.co/spaces/QubitPi/tiger
+
+[Hugging Face sync status badge]: https://img.shields.io/github/actions/workflow/status/QubitPi/tiger/ci-cd.yaml?branch=master&style=for-the-badge&logo=github&logoColor=white&label=Hugging%20Face%20Sync%20Up
+[Hugging Face sync status URL]: https://github.com/QubitPi/tiger/actions/workflows/ci-cd.yaml
+
+[Project Tiger on Hugging Face]: https://huggingface.co/spaces/QubitPi/tiger

app.py

@@ -0,0 +1,236 @@
+import whisper
+import streamlit as st
+from streamlit_lottie import st_lottie
+from utils import write_vtt, write_srt
+import ffmpeg
+import requests
+from typing import Iterator
+from io import StringIO
+import numpy as np
+import pathlib
+import os
+
+st.set_page_config(page_title="Auto Subtitled Video Generator", page_icon=":movie_camera:", layout="wide")
+
+
+# Define a function that we can use to load lottie files from a link.
+def load_lottieurl(url: str):
+    r = requests.get(url)
+    if r.status_code != 200:
+        return None
+    return r.json()
+
+
+APP_DIR = pathlib.Path(__file__).parent.absolute()
+
+LOCAL_DIR = APP_DIR / "local"
+LOCAL_DIR.mkdir(exist_ok=True)
+save_dir = LOCAL_DIR / "output"
+save_dir.mkdir(exist_ok=True)
+
+loaded_model = whisper.load_model("base")
+current_size = "None"
+
+col1, col2 = st.columns([1, 3])
+with col1:
+    lottie = load_lottieurl("https://assets1.lottiefiles.com/packages/lf20_HjK9Ol.json")
+    st_lottie(lottie)
+
+with col2:
+    st.write("""
+    ## Auto Subtitled Video Generator 
+    ##### Upload a video file and get a video with subtitles.
+    ###### ➠ If you want to transcribe the video in its original language, select the task as "Transcribe"
+    ###### ➠ If you want to translate the subtitles to English, select the task as "Translate" 
+    ###### I recommend starting with the base model and then experimenting with the larger models, the small and medium models often work well. """)
+
+
+def change_model(current_size, size):
+    if current_size != size:
+        loaded_model = whisper.load_model(size)
+        return loaded_model
+    else:
+        raise Exception("Model size is the same as the current size.")
+
+
+def inferecence(_loaded_model, uploaded_file, task):
+    with open(f"{save_dir}/input.mp4", "wb") as f:
+        f.write(uploaded_file.read())
+    audio = ffmpeg.input(f"{save_dir}/input.mp4")
+    audio = ffmpeg.output(audio, f"{save_dir}/output.wav", acodec="pcm_s16le", ac=1, ar="16k")
+    ffmpeg.run(audio, overwrite_output=True)
+    if task == "Transcribe":
+        options = dict(task="transcribe", best_of=5)
+        results = _loaded_model.transcribe(f"{save_dir}/output.wav", **options)
+        vtt = getSubs(results["segments"], "vtt", 80)
+        srt = getSubs(results["segments"], "srt", 80)
+        lang = results["language"]
+        return results["text"], vtt, srt, lang
+    elif task == "Translate":
+        options = dict(task="translate", best_of=5)
+        results = _loaded_model.transcribe(f"{save_dir}/output.wav", **options)
+        vtt = getSubs(results["segments"], "vtt", 80)
+        srt = getSubs(results["segments"], "srt", 80)
+        lang = results["language"]
+        return results["text"], vtt, srt, lang
+    else:
+        raise ValueError("Task not supported")
+
+
+def getSubs(segments: Iterator[dict], format: str, maxLineWidth: int) -> str:
+    segmentStream = StringIO()
+
+    if format == 'vtt':
+        write_vtt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
+    elif format == 'srt':
+        write_srt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
+    else:
+        raise Exception("Unknown format " + format)
+
+    segmentStream.seek(0)
+    return segmentStream.read()
+
+
+def generate_subtitled_video(video, audio, transcript):
+    video_file = ffmpeg.input(video)
+    audio_file = ffmpeg.input(audio)
+    ffmpeg.concat(video_file.filter("subtitles", transcript), audio_file, v=1, a=1).output("final.mp4").run(quiet=True,
+                                                                                                            overwrite_output=True)
+    video_with_subs = open("final.mp4", "rb")
+    return video_with_subs
+
+
+def main():
+    size = st.selectbox(
+        "Select Model Size (The larger the model, the more accurate the transcription will be, but it will take longer)",
+        ["tiny", "base", "small", "medium", "large"], index=1)
+    loaded_model = change_model(current_size, size)
+    st.write(f"Model is {'multilingual' if loaded_model.is_multilingual else 'English-only'} "
+             f"and has {sum(np.prod(p.shape) for p in loaded_model.parameters()):,} parameters.")
+    input_file = st.file_uploader("File", type=["mp4", "avi", "mov", "mkv"])
+    # get the name of the input_file
+    if input_file is not None:
+        filename = input_file.name[:-4]
+    else:
+        filename = None
+    task = st.selectbox("Select Task", ["Transcribe", "Translate"], index=0)
+    if task == "Transcribe":
+        if st.button("Transcribe"):
+            results = inferecence(loaded_model, input_file, task)
+            col3, col4 = st.columns(2)
+            col5, col6, col7, col8 = st.columns(4)
+            col9, col10 = st.columns(2)
+            with col3:
+                st.video(input_file)
+
+            with open("transcript.txt", "w+", encoding='utf8') as f:
+                f.writelines(results[0])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.txt"), "rb") as f:
+                datatxt = f.read()
+
+            with open("transcript.vtt", "w+", encoding='utf8') as f:
+                f.writelines(results[1])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.vtt"), "rb") as f:
+                datavtt = f.read()
+
+            with open("transcript.srt", "w+", encoding='utf8') as f:
+                f.writelines(results[2])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.srt"), "rb") as f:
+                datasrt = f.read()
+
+            with col5:
+                st.download_button(label="Download Transcript (.txt)",
+                                   data=datatxt,
+                                   file_name="transcript.txt")
+            with col6:
+                st.download_button(label="Download Transcript (.vtt)",
+                                   data=datavtt,
+                                   file_name="transcript.vtt")
+            with col7:
+                st.download_button(label="Download Transcript (.srt)",
+                                   data=datasrt,
+                                   file_name="transcript.srt")
+            with col9:
+                st.success(
+                    "You can download the transcript in .srt format, edit it (if you need to) and upload it to YouTube to create subtitles for your video.")
+            with col10:
+                st.info(
+                    "Streamlit refreshes after the download button is clicked. The data is cached so you can download the transcript again without having to transcribe the video again.")
+
+            with col4:
+                with st.spinner("Generating Subtitled Video"):
+                    video_with_subs = generate_subtitled_video(f"{save_dir}/input.mp4", f"{save_dir}/output.wav",
+                                                               "transcript.srt")
+                st.video(video_with_subs)
+                st.snow()
+            with col8:
+                st.download_button(label="Download Video with Subtitles",
+                                   data=video_with_subs,
+                                   file_name=f"{filename}_with_subs.mp4")
+    elif task == "Translate":
+        if st.button("Translate to English"):
+            results = inferecence(loaded_model, input_file, task)
+            col3, col4 = st.columns(2)
+            col5, col6, col7, col8 = st.columns(4)
+            col9, col10 = st.columns(2)
+            with col3:
+                st.video(input_file)
+
+            with open("transcript.txt", "w+", encoding='utf8') as f:
+                f.writelines(results[0])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.txt"), "rb") as f:
+                datatxt = f.read()
+
+            with open("transcript.vtt", "w+", encoding='utf8') as f:
+                f.writelines(results[1])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.vtt"), "rb") as f:
+                datavtt = f.read()
+
+            with open("transcript.srt", "w+", encoding='utf8') as f:
+                f.writelines(results[2])
+                f.close()
+            with open(os.path.join(os.getcwd(), "transcript.srt"), "rb") as f:
+                datasrt = f.read()
+
+            with col5:
+                st.download_button(label="Download Transcript (.txt)",
+                                   data=datatxt,
+                                   file_name="transcript.txt")
+            with col6:
+                st.download_button(label="Download Transcript (.vtt)",
+                                   data=datavtt,
+                                   file_name="transcript.vtt")
+            with col7:
+                st.download_button(label="Download Transcript (.srt)",
+                                   data=datasrt,
+                                   file_name="transcript.srt")
+            with col9:
+                st.success(
+                    "You can download the transcript in .srt format, edit it (if you need to) and upload it to YouTube to create subtitles for your video.")
+            with col10:
+                st.info(
+                    "Streamlit refreshes after the download button is clicked. The data is cached so you can download the transcript again without having to transcribe the video again.")
+
+            with col4:
+                with st.spinner("Generating Subtitled Video"):
+                    video_with_subs = generate_subtitled_video(f"{save_dir}/input.mp4", f"{save_dir}/output.wav",
+                                                               "transcript.srt")
+                st.video(video_with_subs)
+                st.snow()
+            with col8:
+                st.download_button(label="Download Video with Subtitles ",
+                                   data=video_with_subs,
+                                   file_name=f"{filename}_with_subs.mp4")
+    else:
+        st.error("Please select a task.")
+
+
+if __name__ == "__main__":
+    main()
+    st.markdown(
+        "###### Made with :heart: by [@QubitPi](https://github.com/QubitPi) [![this is an image link](https://i.imgur.com/thJhzOO.png)](https://buymeacoffee.com/qubitpi)")

languages.py

@@ -0,0 +1,101 @@
+LANGUAGES = {
+    "en": "eng",
+    "zh": "zho",
+    "de": "deu",
+    "es": "spa",
+    "ru": "rus",
+    "ko": "kor",
+    "fr": "fra",
+    "ja": "jpn",
+    "pt": "por",
+    "tr": "tur",
+    "pl": "pol",
+    "ca": "cat",
+    "nl": "nld",
+    "ar": "ara",
+    "sv": "swe",
+    "it": "ita",
+    "id": "ind",
+    "hi": "hin",
+    "fi": "fin",
+    "vi": "vie",
+    "iw": "heb",
+    "uk": "ukr",
+    "el": "ell",
+    "ms": "msa",
+    "cs": "ces",
+    "ro": "ron",
+    "da": "dan",
+    "hu": "hun",
+    "ta": "tam",
+    "no": "nor",
+    "th": "tha",
+    "ur": "urd",
+    "hr": "hrv",
+    "bg": "bul",
+    "lt": "lit",
+    "la": "lat",
+    "mi": "mri",
+    "ml": "mal",
+    "cy": "cym",
+    "sk": "slk",
+    "te": "tel",
+    "fa": "fas",
+    "lv": "lav",
+    "bn": "ben",
+    "sr": "srp",
+    "az": "aze",
+    "sl": "slv",
+    "kn": "kan",
+    "et": "est",
+    "mk": "mkd",
+    "br": "bre",
+    "eu": "eus",
+    "is": "isl",
+    "hy": "hye",
+    "ne": "nep",
+    "mn": "mon",
+    "bs": "bos",
+    "kk": "kaz",
+    "sq": "sqi",
+    "sw": "swa",
+    "gl": "glg",
+    "mr": "mar",
+    "pa": "pan",
+    "si": "sin",
+    "km": "khm",
+    "sn": "sna",
+    "yo": "yor",
+    "so": "som",
+    "af": "afr",
+    "oc": "oci",
+    "ka": "kat",
+    "be": "bel",
+    "tg": "tgk",
+    "sd": "snd",
+    "gu": "guj",
+    "am": "amh",
+    "yi": "yid",
+    "lo": "lao",
+    "uz": "uzb",
+    "fo": "fao",
+    "ht": "hat",
+    "ps": "pus",
+    "tk": "tuk",
+    "nn": "nno",
+    "mt": "mlt",
+    "sa": "san",
+    "lb": "ltz",
+    "my": "mya",
+    "bo": "bod",
+    "tl": "tgl",
+    "mg": "mlg",
+    "as": "asm",
+    "tt": "tat",
+    "haw": "haw",
+    "ln": "lin",
+    "ha": "hau",
+    "ba": "bak",
+    "jw": "jav",
+    "su": "sun",
+}

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,10 @@
+ffmpeg
+ffmpeg_python
+numpy
+pytubefix
+requests
+streamlit
+streamlit_lottie
+torch
+transformers
+openai-whisper

utils.py

@@ -0,0 +1,96 @@
+import textwrap
+import zlib
+from typing import Iterator, TextIO
+
+
+def exact_div(x, y):
+    assert x % y == 0
+    return x // y
+
+
+def str2bool(string):
+    str2val = {"True": True, "False": False}
+    if string in str2val:
+        return str2val[string]
+    else:
+        raise ValueError(f"Expected one of {set(str2val.keys())}, got {string}")
+
+
+def optional_int(string):
+    return None if string == "None" else int(string)
+
+
+def optional_float(string):
+    return None if string == "None" else float(string)
+
+
+def compression_ratio(text) -> float:
+    return len(text) / len(zlib.compress(text.encode("utf-8")))
+
+
+def format_timestamp(seconds: float, always_include_hours: bool = False, fractionalSeperator: str = '.'):
+    assert seconds >= 0, "non-negative timestamp expected"
+    milliseconds = round(seconds * 1000.0)
+
+    hours = milliseconds // 3_600_000
+    milliseconds -= hours * 3_600_000
+
+    minutes = milliseconds // 60_000
+    milliseconds -= minutes * 60_000
+
+    seconds = milliseconds // 1_000
+    milliseconds -= seconds * 1_000
+
+    hours_marker = f"{hours:02d}:" if always_include_hours or hours > 0 else ""
+    return f"{hours_marker}{minutes:02d}:{seconds:02d}{fractionalSeperator}{milliseconds:03d}"
+
+
+def write_txt(transcript: Iterator[dict], file: TextIO):
+    for segment in transcript:
+        print(segment['text'].strip(), file=file, flush=True)
+
+
+def write_vtt(transcript: Iterator[dict], file: TextIO, maxLineWidth=None):
+    print("WEBVTT\n", file=file)
+    for segment in transcript:
+        text = processText(segment['text'], maxLineWidth).replace('-->', '->')
+
+        print(
+            f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
+            f"{text}\n",
+            file=file,
+            flush=True,
+        )
+
+
+def write_srt(transcript: Iterator[dict], file: TextIO, maxLineWidth=None):
+    """
+    Write a transcript to a file in SRT format.
+    Example usage:
+        from pathlib import Path
+        from whisper.utils import write_srt
+        result = transcribe(model, audio_path, temperature=temperature, **args)
+        # save SRT
+        audio_basename = Path(audio_path).stem
+        with open(Path(output_dir) / (audio_basename + ".srt"), "w", encoding="utf-8") as srt:
+            write_srt(result["segments"], file=srt)
+    """
+    for i, segment in enumerate(transcript, start=1):
+        text = processText(segment['text'].strip(), maxLineWidth).replace('-->', '->')
+
+        # write srt lines
+        print(
+            f"{i}\n"
+            f"{format_timestamp(segment['start'], always_include_hours=True, fractionalSeperator=',')} --> "
+            f"{format_timestamp(segment['end'], always_include_hours=True, fractionalSeperator=',')}\n"
+            f"{text}\n",
+            file=file,
+            flush=True,
+        )
+
+def processText(text: str, maxLineWidth=None):
+    if (maxLineWidth is None or maxLineWidth < 0):
+        return text
+
+    lines = textwrap.wrap(text, width=maxLineWidth, tabsize=4)
+    return '\n'.join(lines)