Moved all server files to server/

server/trials/finetuning/inference_fine_tuned.py

@@ -0,0 +1,24 @@
+# Steps to prepare data and submit/check OpenAI finetuning
+# import subprocess
+# subprocess.run("openai tools fine_tunes.prepare_data -f " + "finetuning_dataset.jsonl")
+# export OPENAI_API_KEY=
+# openai api fine_tunes.create -t <TRAIN_FILE_ID_OR_PATH> -m <BASE_MODEL>
+# openai api fine_tunes.list
+
+
+import openai
+
+# Use your OpenAI API Key
+openai.api_key = ""
+
+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 . - > "]
+
+# Give your finetuned model name here
+# "davinci:ft-personal-2023-07-14-10-43-51"
+model_name = ""
+response = openai.Completion.create(
+    model=model_name,
+    prompt=sample_chunks[0])
+
+print(response)

server/trials/finetuning/youtube_scraping.py

@@ -0,0 +1,98 @@
+import json
+import yt_dlp as youtube_dl
+from whisper_jax import FlaxWhisperPipline
+import jax.numpy as jnp
+
+# Function to extract chapter information from a YouTube video URL
+def get_youtube_chapters(video_id):
+    video_url = "https://www.youtube.com/watch?v=" + video_id
+    ydl_opts = {
+        'extract_flat': 'in_playlist',
+        'skip_download': True,
+        'quiet': True,
+    }
+
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        video_info = ydl.extract_info(video_url, download=False)
+
+    chapters = []
+
+    if 'chapters' in video_info:
+        for chapter in video_info['chapters']:
+            start_time = chapter['start_time']
+            end_time = chapter['end_time']
+            title = chapter['title']
+
+            chapters.append({
+                'start': start_time,
+                'end': end_time,
+                'title': title
+            })
+
+    return chapters
+
+
+# Function to extract video transcription using yt_dlp
+def get_youtube_transcription(video_id):
+    ydl_opts = {
+            'format': 'bestaudio/best',
+            'postprocessors': [{
+                    'key': 'FFmpegExtractAudio',
+                    'preferredcodec': 'mp3',
+                    'preferredquality': '192',
+            }],
+            'outtmpl': './artefacts/audio',  # Specify output file path and name
+    }
+
+    # Download the audio
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        ydl.download(["https://www.youtube.com/watch?v=" + video_id])
+    media_file = "./artefacts/audio.mp3"
+
+    pipeline = FlaxWhisperPipline("openai/whisper-" + "tiny",
+                                  dtype=jnp.float16,
+                                  batch_size=16)
+    whisper_result = pipeline(media_file, return_timestamps=True)
+    return whisper_result["chunks"]
+
+
+
+# Function to scrape YouTube video transcripts and chapter information
+def scrape_youtube_data(video_id):
+    transcript_text = get_youtube_transcription(video_id)
+    chapters = get_youtube_chapters(video_id)
+    print("transcript_text", transcript_text)
+    print("chapters", chapters)
+    return transcript_text, chapters
+
+
+# Function to generate fine-tuning dataset from YouTube data
+def generate_finetuning_dataset(video_ids):
+    prompt_completion_pairs = []
+    for video_id in video_ids:
+        transcript_text, chapters = scrape_youtube_data(video_id)
+        if transcript_text is not None and chapters is not None:
+            for chapter in chapters:
+                start_time = chapter["start"]
+                end_time = chapter["end"]
+                chapter_text = chapter["title"]
+
+                prompt = ""
+                for transcript in transcript_text:
+                    if transcript["timestamp"][0] >= start_time and transcript["timestamp"][1] < end_time:
+                        prompt += transcript["text"]
+
+                if prompt is not None:
+                    completion = chapter_text
+                    prompt_completion_pairs.append({"prompt": prompt, "completion": completion})
+
+    return prompt_completion_pairs
+
+
+# Add all the video ids here, the videos must have captions [chapters]
+video_ids = ["yTnSEZIwnkU"]
+dataset = generate_finetuning_dataset(video_ids)
+
+with open("finetuning_dataset.jsonl", "w", encoding="utf-8") as file:
+    for example in dataset:
+        file.write(json.dumps(example) + "\n")

server/trials/server/server_multithreaded.py

@@ -0,0 +1,188 @@
+import asyncio
+import datetime
+import io
+import json
+import threading
+import uuid
+import wave
+from concurrent.futures import ThreadPoolExecutor
+
+import jax.numpy as jnp
+import requests
+from aiohttp import web
+from aiortc import MediaStreamTrack, RTCPeerConnection, RTCSessionDescription
+from aiortc.contrib.media import MediaRelay
+from av import AudioFifo
+from sortedcontainers import SortedDict
+from whisper_jax import FlaxWhisperPipline
+
+from reflector.utils.log_utils import LOGGER
+from reflector.utils.run_utils import CONFIG, Mutex
+
+WHISPER_MODEL_SIZE = CONFIG['WHISPER']["WHISPER_REAL_TIME_MODEL_SIZE"]
+pcs = set()
+relay = MediaRelay()
+data_channel = None
+sorted_message_queue = SortedDict()
+CHANNELS = 2
+RATE = 44100
+CHUNK_SIZE = 256
+pipeline = FlaxWhisperPipline("openai/whisper-" + WHISPER_MODEL_SIZE,
+                              dtype=jnp.float16,
+                              batch_size=16)
+start_time = datetime.datetime.now()
+executor = ThreadPoolExecutor()
+audio_buffer = AudioFifo()
+frame_lock = Mutex(audio_buffer)
+
+
+def channel_log(channel, t, message):
+    print("channel(%s) %s %s" % (channel.label, t, message))
+
+
+def thread_queue_channel_send():
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    try:
+        least_time = sorted_message_queue.keys()[0]
+        message = sorted_message_queue[least_time]
+        if message:
+            del sorted_message_queue[least_time]
+            data_channel.send(message)
+    except Exception as e:
+        print("Exception", str(e))
+        pass
+    loop.run_forever()
+
+
+def get_transcription():
+    while True:
+        with frame_lock.lock() as audio_buffer:
+            frames = audio_buffer.read_many(CHUNK_SIZE * 960, partial=False)
+            if not frames:
+                transcribe = False
+            else:
+                transcribe = True
+
+        if transcribe:
+            print("Transcribing..")
+            try:
+                sorted_message_queue[frames[0].time] = None
+                out_file = io.BytesIO()
+                wf = wave.open(out_file, "wb")
+                wf.setnchannels(CHANNELS)
+                wf.setframerate(RATE)
+                wf.setsampwidth(2)
+
+                for frame in frames:
+                    wf.writeframes(b''.join(frame.to_ndarray()))
+                wf.close()
+
+                whisper_result = pipeline(out_file.getvalue())
+                item = {
+                        'text': whisper_result["text"],
+                        'start_time': str(frames[0].time),
+                        'time': str(datetime.datetime.now())
+                }
+                sorted_message_queue[frames[0].time] = str(item)
+                start_messaging_thread()
+            except Exception as e:
+                print("Exception -> ", str(e))
+
+
+class AudioStreamTrack(MediaStreamTrack):
+    """
+    An audio stream track to send audio frames.
+    """
+
+    kind = "audio"
+
+    def __init__(self, track):
+        super().__init__()  # don't forget this!
+        self.track = track
+
+    async def recv(self):
+        frame = await self.track.recv()
+        audio_buffer.write(frame)
+        return frame
+
+
+def start_messaging_thread():
+    message_thread = threading.Thread(target=thread_queue_channel_send)
+    message_thread.start()
+
+
+def start_transcription_thread(max_threads: int):
+    for i in range(max_threads):
+        t_thread = threading.Thread(target=get_transcription)
+        t_thread.start()
+
+
+async def offer(request: requests.Request):
+    params = await request.json()
+    offer = RTCSessionDescription(sdp=params["sdp"], type=params["type"])
+
+    pc = RTCPeerConnection()
+    pc_id = "PeerConnection(%s)" % uuid.uuid4()
+    pcs.add(pc)
+
+    def log_info(msg: str, *args):
+        LOGGER.info(pc_id + " " + msg, *args)
+
+    log_info("Created for " + request.remote)
+
+    @pc.on("datachannel")
+    def on_datachannel(channel):
+        global data_channel, start_time
+        data_channel = channel
+        channel_log(channel, "-", "created by remote party")
+        start_time = datetime.datetime.now()
+
+        @channel.on("message")
+        def on_message(message: str):
+            channel_log(channel, "<", message)
+            if isinstance(message, str) and message.startswith("ping"):
+                # reply
+                channel.send("pong" + message[4:])
+
+    @pc.on("connectionstatechange")
+    async def on_connectionstatechange():
+        log_info("Connection state is " + pc.connectionState)
+        if pc.connectionState == "failed":
+            await pc.close()
+            pcs.discard(pc)
+
+    @pc.on("track")
+    def on_track(track):
+        log_info("Track " + track.kind + " received")
+        pc.addTrack(AudioStreamTrack(relay.subscribe(track)))
+
+    # handle offer
+    await pc.setRemoteDescription(offer)
+
+    # send answer
+    answer = await pc.createAnswer()
+    await pc.setLocalDescription(answer)
+    return web.Response(
+            content_type="application/json",
+            text=json.dumps({
+                    "sdp": pc.localDescription.sdp,
+                    "type": pc.localDescription.type
+            }),
+    )
+
+
+async def on_shutdown(app: web.Application):
+    coros = [pc.close() for pc in pcs]
+    await asyncio.gather(*coros)
+    pcs.clear()
+
+
+if __name__ == "__main__":
+    app = web.Application()
+    app.on_shutdown.append(on_shutdown)
+    start_transcription_thread(6)
+    app.router.add_post("/offer", offer)
+    web.run_app(
+            app, access_log=None, host="127.0.0.1", port=1250
+    )

server/trials/title_summary/api.py

@@ -0,0 +1,57 @@
+import requests
+import spacy
+
+# Enter the Machine where the LLM is hosted
+LLM_MACHINE_IP = ""
+# This is the URL of text-generation-webui
+URL = f"http://{LLM_MACHINE_IP}:5000/api/v1/generate"
+
+headers = {
+        "Content-Type": "application/json"
+}
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r') as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index - 5]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+
+final_summary = ""
+parts = split_text_file("transcript.txt", 1600)
+
+for part in parts:
+    prompt = f"""
+              ### Human:
+             Given the following text, distill the most important information 
+             into a short summary:  {part}
+
+              ### Assistant:
+              """
+    data = {
+            "prompt": prompt
+    }
+    try:
+        response = requests.post(URL, headers=headers, json=data)
+        print(response.json())
+    except Exception as e:
+        print(str(e))
+
+with open("summary.txt", "w") as sum:
+    sum.write(" ".join(final_summary))

server/trials/title_summary/bert.py

@@ -0,0 +1,43 @@
+import torch
+from transformers import BertTokenizer, BertModel
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the pre-trained BERT model and tokenizer
+model_name = "bert-base-uncased"
+model = BertModel.from_pretrained(model_name)
+tokenizer = BertTokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# Load the SentenceTransformer model
+sentence_transformer_model = SentenceTransformer('average_word_embeddings_glove.6B.300d')
+
+# Define the input text
+text = "Your input text to be summarized goes here."
+
+# Tokenize the text
+tokens = tokenizer.tokenize(text)
+input_ids = tokenizer.convert_tokens_to_ids(tokens)
+input_ids = torch.tensor([input_ids]).to(device)
+
+# Get the BERT model output
+with torch.no_grad():
+    outputs = model(input_ids)[0]  # Extract the last hidden states
+
+# Calculate sentence embeddings
+sentence_embeddings = outputs.mean(dim=1).squeeze().cpu().numpy()
+input_text_embedding = sentence_transformer_model.encode([text])[0]
+
+# Calculate cosine similarity between sentences and input text
+similarity_scores = cosine_similarity([input_text_embedding], sentence_embeddings)
+
+# Sort the sentences by similarity scores in descending order
+sorted_sentences = [sent for _, sent in sorted(zip(similarity_scores[0], sentences), reverse=True)]
+
+# Choose the top sentences as the summary
+num_summary_sentences = 2  # Adjust as needed
+summary = ". ".join(sorted_sentences[:num_summary_sentences])
+print("Summary:", summary)

server/trials/title_summary/gpt2.py

@@ -0,0 +1,101 @@
+# 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 = """
+Summarize the following conversation in 3 key sentences:
+
+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)
+
+# Approach 3
+
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+
+def generate_response(conversation, max_length=100):
+    input_text = ""
+    for entry in conversation:
+        role = entry["role"]
+        content = entry["content"]
+        input_text += f"{role}: {content}\n"
+
+    # Tokenize the entire conversation
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+    # Generate text based on the entire conversation
+    with torch.no_grad():
+        output = model.generate(input_ids, pad_token_id=tokenizer.eos_token_id)
+
+    # Decode the generated text and return it
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+
+if __name__ == "__main__":
+
+    # Call appropriate approach from the main while experimenting
+    model_name = "gpt2"
+    model = GPT2LMHeadModel.from_pretrained(model_name)
+    tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+    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 . "
+    ]
+
+    conversation = [
+            {"role": "system", "content": "Summarize this text"},
+            {"role": "user", "content": " text : " + sample_chunks[0]},
+    ]
+
+    response = generate_response(conversation)
+    print("Response:", response)

server/trials/title_summary/incsum.py

@@ -0,0 +1,157 @@
+import spacy
+import sys
+
+
+# Observe the incremental summaries by performing summaries in chunks
+with open("transcript.txt", "r", encoding="utf-8") as file:
+    transcription = file.read()
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r', encoding="utf-8") as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+
+# Set the chunk length here to split the transcript and test
+MAX_CHUNK_LENGTH = 1000
+
+chunks = split_text_file("transcript.txt", MAX_CHUNK_LENGTH)
+print("Number of chunks", len(chunks))
+
+# Write chunks to file to refer to input vs output, separated by blank lines
+with open("chunks" + str(MAX_CHUNK_LENGTH) + ".txt", "a", encoding="utf-8") as file:
+    for c in chunks:
+        file.write(c + "\n\n")
+
+# If we want to run only a certain model, type the option while running
+# ex. python incsum.py 1 => will run approach 1
+# If no input, will run all approaches
+
+try:
+    index = sys.argv[1]
+except:
+    index = None
+
+# Approach 1 : facebook/bart-large-cnn
+if index == "1" or index is None:
+    SUMMARY_MODEL = "facebook/bart-large-cnn"
+    MIN_LENGTH = 5
+    MAX_LENGTH = 10
+    BEAM_SIZE = 2
+
+    print("Performing chunk summary : " + SUMMARY_MODEL)
+
+    from transformers import BartTokenizer, BartForConditionalGeneration
+
+    tokenizer = BartTokenizer.from_pretrained(SUMMARY_MODEL)
+    model = BartForConditionalGeneration.from_pretrained(SUMMARY_MODEL)
+    summaries = []
+    for c in chunks:
+        input_ids = tokenizer.encode(c,
+                                     truncation=True,
+                                     max_length=MAX_CHUNK_LENGTH,
+                                     padding="max_length",
+                                     return_tensors='pt')
+        summary_ids = model.generate(
+                input_ids,
+                num_beams=BEAM_SIZE,
+                max_length=56,
+                early_stopping=True,
+                length_penalty=1.0)
+        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+        summaries.append(summary)
+
+    with open("bart-summaries.txt", "a", encoding="utf-8") as file:
+        for summary in summaries:
+            file.write(summary + "\n\n")
+
+# Approach 2
+if index == "2" or index is None:
+    print("Performing chunk summary : " + "gpt-neo-1.3B")
+
+    import torch
+    from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+
+    model = GPTNeoForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
+    tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")
+    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+    summaries = []
+
+    for c in chunks:
+        input_ids = tokenizer.encode(c,
+                                     truncation=True,
+                                     return_tensors='pt')
+        input_length = input_ids.shape[1]
+        attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+
+        max_summary_length = 100
+        max_length = input_length + max_summary_length
+
+        output = model.generate(input_ids,
+                                max_length=max_length,
+                                attention_mask=attention_mask,
+                                pad_token_id=model.config.eos_token_id,
+                                num_beams=4,
+                                length_penalty=2.0,
+                                early_stopping=True)
+        summary_ids = output[0, input_length:]
+        summary = tokenizer.decode(summary_ids, skip_special_tokens=True)
+        summaries.append(summary)
+        with open("gptneo1.3B-summaries.txt", "a", encoding="utf-8") as file:
+            file.write(summary + "\n\n")
+
+# Approach 3
+if index == "3" or index is None:
+    print("Performing chunk summary : " + "mpt-7B")
+
+    import torch
+    import transformers
+    from transformers import AutoTokenizer
+
+    config = transformers.AutoConfig.from_pretrained('mosaicml/mpt-7b',
+                                                     trust_remote_code=True)
+    config.attn_config['attn_impl'] = 'triton'
+    config.max_seq_len = 1024
+    config.init_device = "meta"
+
+    model = transformers.AutoModelForCausalLM.from_pretrained(
+            'mosaicml/mpt-7b',
+            trust_remote_code=True,
+            torch_dtype=torch.bfloat16
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained('EleutherAI/gpt-neox-20b')
+
+    summaries = []
+    for c in chunks:
+        input_ids = tokenizer.encode(c, return_tensors="pt")
+        attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+        output = model.generate(input_ids,
+                                max_new_tokens=25,
+                                attention_mask=attention_mask,
+                                pad_token_id=model.config.eos_token_id,
+                                num_return_sequences=1)
+        summary = tokenizer.decode(output[0],
+                                   skip_special_tokens=True)
+        summaries.append(summary)
+
+    with open("mpt-7b-summaries.txt", "a", encoding="utf-8") as file:
+        for summary in summaries:
+            file.write(summary + "\n\n")

server/trials/title_summary/openai_endpoint.py

@@ -0,0 +1,37 @@
+# Use OpenAI API endpoint to send data to OpenAI
+# along with prompts to caption/summarize the conversation
+
+import openai
+
+openai.api_key = ""
+
+# 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"}
+]
+
+model = "gpt-3.5-turbo"
+response = openai.ChatCompletion.create(model=model,
+                                        messages=conversation,
+                                        n=1,
+                                        max_tokens=300)
+
+# Try fine tuned model
+# model = "davinci:ft-personal-2023-07-14-10-43-51"
+# response = openai.Completion.create(model=model,
+#                                         prompt=sample_chunks[0] + " -> ")
+
+caption = response.choices[0]
+print(caption)

server/trials/title_summary/pegasus.py

@@ -0,0 +1,33 @@
+from transformers import PegasusForConditionalGeneration, PegasusTokenizer
+import torch
+# Load the Pegasus model and tokenizer
+model_name = "google/pegasus-large"
+model = PegasusForConditionalGeneration.from_pretrained(model_name)
+tokenizer = PegasusTokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+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 ."]
+
+
+# Define the input text for summarization
+text = sample_chunks[1]
+
+inputs = tokenizer(text, truncation=True, padding="longest", return_tensors="pt").to(device)
+
+# Generate the summary
+summary_ids = model.generate(
+    inputs["input_ids"],
+    attention_mask=inputs["attention_mask"],
+    max_length=200,
+    num_beams=4,
+    length_penalty=2.0,
+    early_stopping=True,
+)
+
+# Decode and print the summary
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+print("Summary:", summary)

server/trials/title_summary/t5.py

@@ -0,0 +1,27 @@
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+import torch
+# Load the T5 model and tokenizer
+model_name = "t5-base"
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+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 ."]
+
+
+# Define the input text for summarization
+text = "Summarize the following text in 3 key points. text : " + sample_chunks[1]
+
+# Tokenize the input text
+inputs = tokenizer.encode(text, return_tensors="pt").to(device)
+
+# Generate the summary
+summary_ids = model.generate(inputs, max_length=1000, num_beams=4, early_stopping=True)
+
+# Decode and print the summary
+summary = tokenizer.decode(summary_ids.squeeze(), skip_special_tokens=True)
+print("Summary:", summary)

server/trials/title_summary/vicuna.py

@@ -0,0 +1,44 @@
+from gpt4all import GPT4All
+
+model = GPT4All("/Users/gokulmohanarangan/Library/Application Support/nomic.ai/GPT4All/ggml-vicuna-13b-1.1-q4_2.bin")
+
+import spacy
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r') as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+parts = split_text_file("transcript.txt", 1800)
+final_summary = []
+for part in parts:
+       prompt = f"""
+              ### Human:
+              Summarize the following text without missing any key points and action items.
+                     
+              {part}
+              ### Assistant:
+              """
+       output = model.generate(prompt)
+       final_summary.append(output)
+
+
+with open("sum.txt", "w") as sum:
+       sum.write(" ".join(final_summary))

server/trials/whisper-jax/whisjax.py

@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+
+# summarize https://www.youtube.com/watch?v=imzTxoEDH_g
+# summarize https://www.sprocket.org/video/cheesemaking.mp4 summary.txt
+# summarize podcast.mp3 summary.txt
+
+import argparse
+import os
+import re
+import subprocess
+import tempfile
+from datetime import datetime
+from urllib.parse import urlparse
+
+import jax.numpy as jnp
+import moviepy.editor
+import nltk
+import yt_dlp as youtube_dl
+from whisper_jax import FlaxWhisperPipline
+
+from ...utils.file_utils import download_files, upload_files
+from ...utils.log_utils import LOGGER
+from ...utils.run_utils import CONFIG
+from ...utils.text_utils import post_process_transcription, summarize
+from ...utils.viz_utils import create_talk_diff_scatter_viz, create_wordcloud
+
+nltk.download('punkt', quiet=True)
+nltk.download('stopwords', quiet=True)
+
+WHISPER_MODEL_SIZE = CONFIG['WHISPER']["WHISPER_MODEL_SIZE"]
+NOW = datetime.now()
+
+if not os.path.exists('../../artefacts'):
+    os.makedirs('../../artefacts')
+
+
+def init_argparse() -> argparse.ArgumentParser:
+    """
+    Parse the CLI arguments
+    :return: parser object
+    """
+    parser = argparse.ArgumentParser(
+            usage="%(prog)s [OPTIONS] <LOCATION> <OUTPUT>",
+            description="Creates a transcript of a video or audio file, then"
+                        " summarizes it using ChatGPT."
+    )
+
+    parser.add_argument("-l", "--language",
+                        help="Language that the summary should be written in",
+                        type=str,
+                        default="english",
+                        choices=['english', 'spanish', 'french', 'german',
+                                 'romanian'])
+    parser.add_argument("location")
+    return parser
+
+
+def main():
+    parser = init_argparse()
+    args = parser.parse_args()
+
+    # Parse the location string that was given to us, and figure out if it's a
+    # local file (audio or video), a YouTube URL, or a URL referencing an
+    # audio or video file.
+    url = urlparse(args.location)
+
+    # S3 : Pull artefacts to S3 bucket ?
+
+    media_file = ""
+    if url.scheme == 'http' or url.scheme == 'https':
+        # Check if we're being asked to retreive a YouTube URL, which is
+        # handled differently, as we'll use a secondary site to download
+        # the video first.
+        if re.search('youtube.com', url.netloc, re.IGNORECASE):
+            # Download the lowest resolution YouTube video
+            # (since we're just interested in the audio).
+            # It will be saved to the current directory.
+            LOGGER.info("Downloading YouTube video at url: " + args.location)
+
+            # Create options for the download
+            ydl_opts = {
+                    'format': 'bestaudio/best',
+                    'postprocessors': [{
+                            'key': 'FFmpegExtractAudio',
+                            'preferredcodec': 'mp3',
+                            'preferredquality': '192',
+                    }],
+                    '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 = "../artefacts/audio.mp3"
+
+            LOGGER.info("Saved downloaded YouTube video to: " + media_file)
+        else:
+            # XXX - Download file using urllib, check if file is
+            # audio/video using python-magic
+            LOGGER.info(f"Downloading file at url: {args.location}")
+            LOGGER.info("  XXX - This method hasn't been implemented yet.")
+    elif url.scheme == '':
+        media_file = url.path
+        # If file is not present locally, take it from S3 bucket
+        if not os.path.exists(media_file):
+            download_files([media_file])
+
+        if media_file.endswith(".m4a"):
+            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()
+
+    # Handle video
+    if not media_file.endswith(".mp3"):
+        try:
+            video = moviepy.editor.VideoFileClip(media_file)
+            audio_filename = tempfile.NamedTemporaryFile(suffix=".mp3",
+                                                         delete=False).name
+            video.audio.write_audiofile(audio_filename, logger=None)
+            LOGGER.info(f"Extracting audio to: {audio_filename}")
+        # Handle audio only file
+        except Exception:
+            audio = moviepy.editor.AudioFileClip(media_file)
+            audio_filename = tempfile.NamedTemporaryFile(suffix=".mp3",
+                                                         delete=False).name
+            audio.write_audiofile(audio_filename, logger=None)
+    else:
+        audio_filename = media_file
+
+    LOGGER.info("Finished extracting audio")
+    LOGGER.info("Transcribing")
+    # Convert the audio to text using the OpenAI Whisper model
+    pipeline = FlaxWhisperPipline("openai/whisper-" + WHISPER_MODEL_SIZE,
+                                  dtype=jnp.float16,
+                                  batch_size=16)
+    whisper_result = pipeline(audio_filename, return_timestamps=True)
+    LOGGER.info("Finished transcribing file")
+
+    whisper_result = post_process_transcription(whisper_result)
+
+    transcript_text = ""
+    for chunk in whisper_result["chunks"]:
+        transcript_text += chunk["text"]
+
+    with open("./artefacts/transcript_" + NOW.strftime("%m-%d-%Y_%H:%M:%S") +
+              ".txt", "w") as transcript_file:
+        transcript_file.write(transcript_text)
+
+    with open("./artefacts/transcript_with_timestamp_" +
+              NOW.strftime("%m-%d-%Y_%H:%M:%S") + ".txt",
+              "w") as transcript_file_timestamps:
+        transcript_file_timestamps.write(str(whisper_result))
+
+    LOGGER.info("Creating word cloud")
+    create_wordcloud(NOW)
+
+    LOGGER.info("Performing talk-diff and talk-diff visualization")
+    create_talk_diff_scatter_viz(NOW)
+
+    # S3 : Push artefacts to S3 bucket
+    prefix = "./artefacts/"
+    suffix = NOW.strftime("%m-%d-%Y_%H:%M:%S")
+    files_to_upload = [prefix + "transcript_" + suffix + ".txt",
+                       prefix + "transcript_with_timestamp_" + suffix + ".txt",
+                       prefix + "df_" + suffix + ".pkl",
+                       prefix + "wordcloud_" + suffix + ".png",
+                       prefix + "mappings_" + suffix + ".pkl",
+                       prefix + "scatter_" + suffix + ".html"]
+    upload_files(files_to_upload)
+
+    summarize(transcript_text, NOW, False, False)
+
+    LOGGER.info("Summarization completed")
+
+    # Summarization takes a lot of time, so do this separately at the end
+    files_to_upload = [prefix + "summary_" + suffix + ".txt"]
+    upload_files(files_to_upload)
+
+
+if __name__ == "__main__":
+    main()

server/trials/whisper-jax/whisjax_realtime.py

@@ -0,0 +1,151 @@
+#!/usr/bin/env python3
+
+import time
+import wave
+from datetime import datetime
+
+import jax.numpy as jnp
+import pyaudio
+from pynput import keyboard
+from termcolor import colored
+from whisper_jax import FlaxWhisperPipline
+
+from ...utils.file_utils import upload_files
+from ...utils.log_utils import LOGGER
+from ...utils.run_utils import CONFIG
+from ...utils.text_utils import post_process_transcription, summarize
+from ...utils.viz_utils import create_talk_diff_scatter_viz, create_wordcloud
+
+WHISPER_MODEL_SIZE = CONFIG['WHISPER']["WHISPER_MODEL_SIZE"]
+
+FRAMES_PER_BUFFER = 8000
+FORMAT = pyaudio.paInt16
+CHANNELS = 2
+RATE = 96000
+RECORD_SECONDS = 15
+NOW = datetime.now()
+
+
+def main():
+    p = pyaudio.PyAudio()
+    AUDIO_DEVICE_ID = -1
+    for i in range(p.get_device_count()):
+        if p.get_device_info_by_index(i)["name"] == \
+                CONFIG["AUDIO"]["BLACKHOLE_INPUT_AGGREGATOR_DEVICE_NAME"]:
+            AUDIO_DEVICE_ID = i
+    audio_devices = p.get_device_info_by_index(AUDIO_DEVICE_ID)
+    stream = p.open(
+            format=FORMAT,
+            channels=CHANNELS,
+            rate=RATE,
+            input=True,
+            frames_per_buffer=FRAMES_PER_BUFFER,
+            input_device_index=int(audio_devices['index'])
+    )
+
+    pipeline = FlaxWhisperPipline("openai/whisper-" +
+                                  CONFIG["WHISPER"]["WHISPER_REAL_TIME_MODEL_SIZE"],
+                                  dtype=jnp.float16,
+                                  batch_size=16)
+
+    transcription = ""
+
+    TEMP_AUDIO_FILE = "temp_audio.wav"
+    global proceed
+    proceed = True
+
+    def on_press(key):
+        if key == keyboard.Key.esc:
+            global proceed
+            proceed = False
+
+    transcript_with_timestamp = {"text": "", "chunks": []}
+    last_transcribed_time = 0.0
+
+    listener = keyboard.Listener(on_press=on_press)
+    listener.start()
+    print("Attempting real-time transcription.. Listening...")
+
+    try:
+        while proceed:
+            frames = []
+            start_time = time.time()
+            for i in range(0, int(RATE / FRAMES_PER_BUFFER * RECORD_SECONDS)):
+                data = stream.read(FRAMES_PER_BUFFER,
+                                   exception_on_overflow=False)
+                frames.append(data)
+            end_time = time.time()
+
+            wf = wave.open(TEMP_AUDIO_FILE, 'wb')
+            wf.setnchannels(CHANNELS)
+            wf.setsampwidth(p.get_sample_size(FORMAT))
+            wf.setframerate(RATE)
+            wf.writeframes(b''.join(frames))
+            wf.close()
+
+            whisper_result = pipeline(TEMP_AUDIO_FILE, return_timestamps=True)
+            timestamp = whisper_result["chunks"][0]["timestamp"]
+            start = timestamp[0]
+            end = timestamp[1]
+            if end is None:
+                end = start + 15.0
+            duration = end - start
+            item = {'timestamp': (last_transcribed_time,
+                                  last_transcribed_time + duration),
+                    'text': whisper_result['text'],
+                    'stats': (str(end_time - start_time), str(duration))
+                    }
+            last_transcribed_time = last_transcribed_time + duration
+            transcript_with_timestamp["chunks"].append(item)
+            transcription += whisper_result['text']
+
+            print(colored("<START>", "yellow"))
+            print(colored(whisper_result['text'], 'green'))
+            print(colored("<END> Recorded duration: " +
+                          str(end_time - start_time) +
+                          " | Transcribed duration: " +
+                          str(duration), "yellow"))
+
+    except Exception as exception:
+        print(str(exception))
+    finally:
+        with open("real_time_transcript_" + NOW.strftime("%m-%d-%Y_%H:%M:%S")
+                  + ".txt", "w", encoding="utf-8") as file:
+            file.write(transcription)
+
+        with open("real_time_transcript_with_timestamp_" +
+                  NOW.strftime("%m-%d-%Y_%H:%M:%S") + ".txt", "w",
+                  encoding="utf-8") as file:
+            transcript_with_timestamp["text"] = transcription
+            file.write(str(transcript_with_timestamp))
+
+    transcript_with_timestamp = \
+        post_process_transcription(transcript_with_timestamp)
+
+    LOGGER.info("Creating word cloud")
+    create_wordcloud(NOW, True)
+
+    LOGGER.info("Performing talk-diff and talk-diff visualization")
+    create_talk_diff_scatter_viz(NOW, True)
+
+    # S3 : Push artefacts to S3 bucket
+    suffix = NOW.strftime("%m-%d-%Y_%H:%M:%S")
+    files_to_upload = ["real_time_transcript_" + suffix + ".txt",
+                       "real_time_transcript_with_timestamp_" + suffix + ".txt",
+                       "real_time_df_" + suffix + ".pkl",
+                       "real_time_wordcloud_" + suffix + ".png",
+                       "real_time_mappings_" + suffix + ".pkl",
+                       "real_time_scatter_" + suffix + ".html"]
+    upload_files(files_to_upload)
+
+    summarize(transcript_with_timestamp["text"], NOW, True, True)
+
+    LOGGER.info("Summarization completed")
+
+    # Summarization takes a lot of time, so do this separately at the end
+    files_to_upload = ["real_time_summary_" + suffix + ".txt"]
+    upload_files(files_to_upload)
+
+
+if __name__ == "__main__":
+    main()