Initial commit

.gitignore

@@ -0,0 +1,4 @@
+venv/
+ui/__pycache__/
+modules/__pycache__/
+modules/yt_tmp.wav

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 2023 jhj0517
+
+   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.

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+from modules.model_Inference import WhisperInference
+from ui.htmls import CSS,MARKDOWN_TITLE,MARKDOWN_NOTE
+from modules.youtube_manager import get_ytmetas
+
+def on_change_models(model_size):
+    translatable_model = ["large","large-v1","large-v2"]
+    if model_size not in translatable_model:
+        return gr.Checkbox.update(visible=False,value=False,interactive=False)
+    else:
+        return gr.Checkbox.update(visible=True,value=False,label="Translate to English?",interactive=True) 
+
+whisper_inf = WhisperInference()
+block = gr.Blocks(css=CSS).queue(api_open=False)
+
+with block:
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown(MARKDOWN_TITLE,elem_id="md_project")
+            gr.Markdown(MARKDOWN_NOTE,elem_id="md_note")
+    with gr.Tabs():
+        with gr.TabItem("File"): # tab1    
+            with gr.Row():
+                input_file = gr.Files(type="file", label="Upload File here",file_types=["audio","video"])
+            with gr.Row():
+                dd_model = gr.Dropdown(choices=whisper_inf.available_models,value="tiny",label="Model")
+                dd_lang = gr.Dropdown(choices=["Automatic Detection"]+whisper_inf.available_langs,value="Automatic Detection",label="Language")
+                dd_subformat = gr.Dropdown(["SRT","WebVTT"],value="SRT",label="Subtitle Format")
+            with gr.Row():
+                cb_translate = gr.Checkbox(value=False,visible=False,label="Translate to English?",interactive=True) 
+            with gr.Row():
+                btn_run = gr.Button("GENERATE SUBTITLE FILE",variant="primary")
+            with gr.Row():
+                tb_indicator = gr.Textbox(label="Output")
+
+            btn_run.click(fn=whisper_inf.transcribe_file,inputs=[input_file,dd_model,dd_lang,dd_subformat,cb_translate],outputs=[tb_indicator])    
+            dd_model.change(fn=on_change_models,inputs=[dd_model],outputs=[cb_translate])
+        
+        with gr.TabItem("Youtube"): # tab2
+            with gr.Row():
+                tb_youtubelink = gr.Textbox(label="Youtube Link" ) 
+            with gr.Row().style(equal_height=True):
+                with gr.Column():
+                    img_thumbnail = gr.Image(label="Youtube Thumbnail")
+                with gr.Column():
+                    tb_title = gr.Label(label="Youtube Title")
+                    tb_description = gr.Textbox(label="Youtube Description",max_lines=15)
+            with gr.Row():
+                dd_model = gr.Dropdown(choices=whisper_inf.available_models,value="tiny",label="Model")
+                dd_lang = gr.Dropdown(choices=["Automatic Detection"]+whisper_inf.available_langs,value="Automatic Detection",label="Language")
+                dd_subformat = gr.Dropdown(choices=["SRT","WebVTT"],value="SRT",label="Subtitle Format")
+            with gr.Row():
+                cb_translate = gr.Checkbox(value=False,visible=False,label="Translate to English?",interactive=True) 
+            with gr.Row():
+                btn_run = gr.Button("GENERATE SUBTITLE FILE",variant="primary")
+            with gr.Row():
+                tb_indicator = gr.Textbox(label="Output")
+
+            btn_run.click(fn=whisper_inf.transcribe_youtube,inputs=[tb_youtubelink,dd_model,dd_lang,dd_subformat,cb_translate],outputs=[tb_indicator])    
+            tb_youtubelink.change(get_ytmetas,inputs=[tb_youtubelink],outputs=[img_thumbnail,tb_title,tb_description])
+            dd_model.change(fn=on_change_models,inputs=[dd_model],outputs=[cb_translate])
+
+        with gr.TabItem("Mic"): # tab3
+            with gr.Row():
+                mic_input = gr.Microphone(label="Record with Mic",type="filepath",interactive=True)
+            with gr.Row():
+                dd_model = gr.Dropdown(choices=whisper_inf.available_models,value="tiny",label="Model")
+                dd_lang = gr.Dropdown(choices=["Automatic Detection"]+whisper_inf.available_langs,value="Automatic Detection",label="Language")
+                dd_subformat = gr.Dropdown(["SRT","WebVTT"],value="SRT",label="Subtitle Format")
+            with gr.Row():
+                cb_translate = gr.Checkbox(value=False,visible=False,label="Translate to English?",interactive=True) 
+            with gr.Row():
+                btn_run = gr.Button("GENERATE SUBTITLE FILE",variant="primary")
+            with gr.Row():
+                tb_indicator = gr.Textbox(label="Output")
+
+            btn_run.click(fn=whisper_inf.transcribe_mic,inputs=[mic_input,dd_model,dd_lang,dd_subformat,cb_translate],outputs=[tb_indicator])    
+            dd_model.change(fn=on_change_models,inputs=[dd_model],outputs=[cb_translate])   
+    
+block.launch()
+

modules/model_Inference.py

@@ -0,0 +1,135 @@
+import whisper
+from modules.subtitle_manager import get_srt,get_vtt,safe_filename
+from modules.youtube_manager import get_ytdata,get_ytaudio
+import gradio as gr
+import os
+
+DEFAULT_MODEL_SIZE="tiny"
+
+class WhisperInference():
+    def __init__(self):
+        print("\nInitializing Model..\n")
+        self.current_model_size = DEFAULT_MODEL_SIZE
+        self.model = whisper.load_model(name=DEFAULT_MODEL_SIZE,download_root="models")
+        self.available_models = ["tiny","tiny.en"]
+        self.available_langs = sorted(list(whisper.tokenizer.LANGUAGES.values()))
+
+    def transcribe_file(self,fileobjs
+                        ,model_size,lang,subformat,istranslate,
+                        progress=gr.Progress()):
+
+        def progress_callback(progress_value):
+            progress(progress_value,desc="Transcribing..")
+        
+        if model_size != self.current_model_size:
+            progress(0,desc="Initializing Model..")
+            self.current_model_size = model_size
+            self.model = whisper.load_model(name=model_size,download_root="models")
+
+        if lang == "Automatic Detection" :
+            lang = None    
+
+        progress(0,desc="Loading Audio..")    
+
+        files_info = {}
+        for fileobj in fileobjs: 
+            print(f"\n\n {fileobj.name} \n\n")
+
+            audio = whisper.load_audio(fileobj.name)
+
+            translatable_model = ["large","large-v1","large-v2"]
+            if istranslate and self.current_model_size in translatable_model:
+                result = self.model.transcribe(audio=audio,language=lang,verbose=False,task="translate",progress_callback=progress_callback)
+            else : 
+                result = self.model.transcribe(audio=audio,language=lang,verbose=False,progress_callback=progress_callback)
+
+            progress(1,desc="Completed!")
+
+            file_name, file_ext = os.path.splitext(os.path.basename(fileobj.orig_name))
+            file_name = file_name[:-9]
+            file_name = safe_filename(file_name)
+
+            if subformat == "SRT":
+                subtitle = get_srt(result["segments"])
+            elif subformat == "WebVTT":
+                subtitle = get_vtt(result["segments"])
+
+            files_info[file_name] = subtitle
+
+        total_result = ''
+        for file_name,subtitle in files_info.items():
+            total_result+='------------------------------------\n'
+            total_result+=f'{file_name}\n\n'  
+            total_result+=f'{subtitle}'  
+
+        return f"\n\n{total_result}"
+    
+    def transcribe_youtube(self,youtubelink
+                        ,model_size,lang,subformat,istranslate,
+                        progress=gr.Progress()):
+        
+        def progress_callback(progress_value):
+            progress(progress_value,desc="Transcribing..")
+
+        if model_size != self.current_model_size:
+            progress(0,desc="Initializing Model..")
+            self.current_model_size = model_size
+            self.model = whisper.load_model(name=model_size,download_root="models")
+
+        if lang == "Automatic Detection" :
+            lang = None    
+
+        progress(0,desc="Loading Audio from Youtube..")    
+        yt = get_ytdata(youtubelink)
+        audio = whisper.load_audio(get_ytaudio(yt))
+
+        translatable_model = ["large","large-v1","large-v2"]
+        if istranslate and self.current_model_size in translatable_model:
+            result = self.model.transcribe(audio=audio,language=lang,verbose=False,task="translate",progress_callback=progress_callback)
+        else : 
+            result = self.model.transcribe(audio=audio,language=lang,verbose=False,progress_callback=progress_callback)
+
+        progress(1,desc="Completed!")
+
+        file_name = safe_filename(yt.title)
+
+        if subformat == "SRT":
+            subtitle = get_srt(result["segments"])
+        elif subformat == "WebVTT":
+            subtitle = get_vtt(result["segments"])
+
+        return f"\n\n{subtitle}"
+    
+    def transcribe_mic(self,micaudio
+                    ,model_size,lang,subformat,istranslate,
+                    progress=gr.Progress()):
+
+        def progress_callback(progress_value):
+            progress(progress_value,desc="Transcribing..")
+        
+        if model_size != self.current_model_size:
+            progress(0,desc="Initializing Model..")
+            self.current_model_size = model_size
+            self.model = whisper.load_model(name=model_size,download_root="models")
+
+        if lang == "Automatic Detection" :
+            lang = None    
+
+        progress(0,desc="Loading Audio..")    
+
+        translatable_model = ["large","large-v1","large-v2"]
+        if istranslate and self.current_model_size in translatable_model:
+            result = self.model.transcribe(audio=micaudio,language=lang,verbose=False,task="translate",progress_callback=progress_callback)
+        else : 
+            result = self.model.transcribe(audio=micaudio,language=lang,verbose=False,progress_callback=progress_callback)
+
+        progress(1,desc="Completed!")
+
+        if subformat == "SRT":
+            subtitle = get_srt(result["segments"])
+        elif subformat == "WebVTT":
+            subtitle = get_vtt(result["segments"])
+            
+        return f"\n\n{subtitle}"
+    
+    

modules/subtitle_manager.py

@@ -0,0 +1,43 @@
+import re
+
+def timeformat_srt(time):
+    hours = time//3600
+    minutes = (time - hours*3600)//60
+    seconds = time - hours*3600 - minutes*60
+    milliseconds = (time - int(time))*1000
+    return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d},{int(milliseconds):03d}"
+
+def timeformat_vtt(time):
+    hours = time//3600
+    minutes = (time - hours*3600)//60
+    seconds = time - hours*3600 - minutes*60
+    milliseconds = (time - int(time))*1000
+    return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d}.{int(milliseconds):03d}"
+
+def write_srt(subtitle,output_file):
+    with open(output_file, 'w', encoding='utf-8') as f:
+        f.write(subtitle)
+
+def write_vtt(subtitle,output_file):
+    with open(output_file, 'w', encoding='utf-8') as f:
+        f.write(subtitle)        
+
+def get_srt(segments):
+    output = ""
+    for i, segment in enumerate(segments):
+        output += f"{i+1}\n"
+        output += f"{timeformat_srt(segment['start'])} --> {timeformat_srt(segment['end'])}\n"
+        output += f"{segment['text']}\n\n"        
+    return output    
+
+def get_vtt(segments):
+    output = "WebVTT\n\n"
+    for i, segment in enumerate(segments):
+        output += f"{i+1}\n"
+        output += f"{timeformat_vtt(segment['start'])} --> {timeformat_vtt(segment['end'])}\n"
+        output += f"{segment['text']}\n\n"        
+    return output
+
+def safe_filename(name):
+    INVALID_FILENAME_CHARS = r'[<>:"/\\|?*\x00-\x1f]'
+    return re.sub(INVALID_FILENAME_CHARS, '_', name)

modules/youtube_manager.py

@@ -0,0 +1,11 @@
+from pytube import YouTube
+
+def get_ytdata(link):
+    return YouTube(link)
+
+def get_ytmetas(link):
+    yt = YouTube(link)
+    return yt.thumbnail_url,yt.title,yt.description
+
+def get_ytaudio(ytdata:YouTube):
+    return ytdata.streams.get_audio_only().download(filename="modules/yt_tmp.wav")

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/jhj0517/jhj0517-whisper.git
+pytube

ui/htmls.py

@@ -0,0 +1,55 @@
+CSS = """
+.bmc-button {
+    padding: 2px 5px;
+    border-radius: 5px;
+    background-color: #FF813F;
+    color: white;
+    box-shadow: 0px 1px 2px rgba(0, 0, 0, 0.3);
+    text-decoration: none;
+    display: inline-block;
+    font-size: 20px;
+    margin: 2px;
+    cursor: pointer;
+    -webkit-transition: background-color 0.3s ease;
+    -ms-transition: background-color 0.3s ease;
+    transition: background-color 0.3s ease;
+}
+.bmc-button:hover,
+.bmc-button:active,
+.bmc-button:focus {
+    background-color: #FF5633;
+}
+.markdown {
+    margin-bottom: 0;
+    padding-bottom: 0;
+}
+.tabs {
+    margin-top: 0;
+    padding-top: 0;
+}
+
+#md_project a {
+  color: black;
+  text-decoration: none;
+}
+#md_project a:hover {
+  text-decoration: underline;
+}
+
+#md_note a {
+  color: black;
+}
+#md_note a:hover {
+  text-decoration: underline;
+}
+"""
+
+MARKDOWN_TITLE = """
+### [Whisper Web-UI](https://github.com/jhj0517/Whsiper-WebUI) 
+"""
+MARKDOWN_NOTE = """
+### To run it locally, check [here !](https://github.com/jhj0517/Whsiper-WebUI) 
+Note: Only the **"tiny"** and **"tiny.en"** models are supported in this space due to the free CPU provided by Hugging Face. 
+
+If you want to run every Whisper model, you should do it in a local environment.
+"""