Merge pull request #28 from Monadical-SAS/feat/gokul

Push summarization trials

scripts/clear_artefacts.sh

@@ -16,9 +16,15 @@ summary_file_pattern="summary_*.txt"
 pickle_file_pattern="*.pkl"
 html_file_pattern="*.html"
 png_file_pattern="wordcloud*.png"
+mp3_file_pattern="*.mp3"
+mp4_file_pattern="*.mp4"
+m4a_file_pattern="*.m4a"
 
 find "$directory" -type f -name "$transcript_file_pattern" -delete
 find "$directory" -type f -name "$summary_file_pattern" -delete
 find "$directory" -type f -name "$pickle_file_pattern" -delete
 find "$directory" -type f -name "$html_file_pattern" -delete
 find "$directory" -type f -name "$png_file_pattern" -delete
+find "$directory" -type f -name "$mp3_file_pattern" -delete
+find "$directory" -type f -name "$mp4_file_pattern" -delete
+find "$directory" -type f -name "$m4a_file_pattern" -delete

trials/gpt2.py

@@ -0,0 +1,55 @@
+# Approach 1
+from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+
+model_name = 'EleutherAI/gpt-neo-1.3B'
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPTNeoForCausalLM.from_pretrained(model_name)
+
+conversation = """
+We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI .
+Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development .
+Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations .
+Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude .
+Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council .
+Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas .
+"""
+
+input_ids = tokenizer.encode(conversation, return_tensors='pt')
+
+output = model.generate(input_ids,
+                        max_length=30,
+                        num_return_sequences=1)
+
+caption = tokenizer.decode(output[0], skip_special_tokens=True)
+print("Caption:", caption[len(input_ids):])
+
+
+# Approach 2
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+model_name = "gpt2"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+model.eval()
+
+text = """
+You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple .  If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody .  Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me .  So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody .  And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . "         
+"""
+
+tokenizer.pad_token = tokenizer.eos_token
+input_ids = tokenizer.encode(text,
+                             max_length=100,
+                             truncation=True,
+                             return_tensors="pt")
+attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+output = model.generate(input_ids,
+                        max_new_tokens=20,
+                        num_return_sequences=1,
+                        num_beams=2,
+                        attention_mask=attention_mask)
+
+chapter_titles = [tokenizer.decode(output[i], skip_special_tokens=True) for i in range(output.shape[0])]
+for i, title in enumerate(chapter_titles):
+    print("Caption: ", title)

trials/openai_endpoint.py

@@ -0,0 +1,30 @@
+# Use OpenAI API endpoint to send data to OpenAI
+# along with prompts to caption/summarize the conversation
+
+import openai
+
+openai.api_key = "***REMOVED***"
+
+# to caption, user prompt used : "caption this conversation"
+#             max_tokens=20
+
+# to incremental summarize, user prompt used : "summarize this conversation in a few sentences by taking key points"
+#               max_tokens=300
+
+sample_chunks = ["You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple .  If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody .  Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me .  So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody .  And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . ",
+                 " We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI . Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development . Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations . Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude .  Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council . Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas ."]
+
+conversation = [
+    {"role": "system",
+     "content":  sample_chunks[1]},
+    {"role": "user",
+     "content": "summarize this conversation in a few sentences by taking key points"}
+]
+
+response = openai.ChatCompletion.create(model="gpt-3.5-turbo",
+                                        messages=conversation,
+                                        n=1,
+                                        max_tokens=300)
+
+caption = response.choices[0].message.content.strip()
+print(caption)

whisjax.py

@@ -85,13 +85,13 @@ def main():
                             'preferredcodec': 'mp3',
                             'preferredquality': '192',
                     }],
-                    'outtmpl': 'audio',  # Specify output file path and name
+                    'outtmpl': './artefacts/audio',  # Specify output file path and name
             }
 
             # Download the audio
             with youtube_dl.YoutubeDL(ydl_opts) as ydl:
                 ydl.download([args.location])
-            media_file = "audio.mp3"
+            media_file = "./artefacts/audio.mp3"
 
             logger.info("Saved downloaded YouTube video to: " + media_file)
         else:
@@ -106,8 +106,8 @@ def main():
             download_files([media_file])
 
         if media_file.endswith(".m4a"):
-            subprocess.run(["ffmpeg", "-i", media_file, f"{media_file}.mp4"])
-            media_file = f"{media_file}.mp4"
+            subprocess.run(["ffmpeg", "-i", media_file, f"./artefacts/{media_file}.mp4"])
+            media_file = f"./artefacts/{media_file}.mp4"
     else:
         print("Unsupported URL scheme: " + url.scheme)
         quit()