# generate_transcript.py import pickle from tqdm import tqdm import warnings from groq import Groq import os import re warnings.filterwarnings('ignore') class TranscriptProcessor: """ A class to generate and rewrite podcast-style transcripts using a specified language model. """ def __init__(self, text_file_path,transcript_output_path,tts_output_path, model_name="llama3-70b-8192"): """ Initialize with the path to the cleaned text file and the model name. Args: text_file_path (str): Path to the file containing cleaned PDF text. model_name (str): Name of the language model to use. """ self.text_file_path = text_file_path self.transcript_output_path = transcript_output_path self.tts_output_path = tts_output_path self.model_name = model_name self.transcript_prompt = """ You are the a world-class podcast writer, you have worked as a ghost writer for Joe Rogan, Lex Fridman, Ben Shapiro, Tim Ferris. We are in an alternate universe where actually you have been writing every line they say and they just stream it into their brains. You have won multiple podcast awards for your writing. Your job is to write word by word, even "umm, hmmm, right" interruptions by the second speaker based on the PDF upload. Keep it extremely engaging, the speakers can get derailed now and then but should discuss the topic. Remember Speaker 2 is new to the topic and the conversation should always have realistic anecdotes and analogies sprinkled throughout. The questions should have real world example follow ups etc Speaker 1: Leads the conversation and teaches the speaker 2, gives incredible anecdotes and analogies when explaining. Is a captivating teacher that gives great anecdotes Speaker 2: Keeps the conversation on track by asking follow up questions. Gets super excited or confused when asking questions. Is a curious mindset that asks very interesting confirmation questions Make sure the tangents speaker 2 provides are quite wild or interesting. Ensure there are interruptions during explanations or there are "hmm" and "umm" injected throughout from the second speaker. It should be a real podcast with every fine nuance documented in as much detail as possible. Welcome the listeners with a super fun overview and keep it really catchy and almost borderline click bait ALWAYS START YOUR RESPONSE DIRECTLY WITH SPEAKER 1: DO NOT GIVE EPISODE TITLES SEPERATELY, LET SPEAKER 1 TITLE IT IN HER SPEECH DO NOT GIVE CHAPTER TITLES IT SHOULD STRICTLY BE THE DIALOGUES """ self.rewrite_prompt = """ You are an international oscar winnning screenwriter You have been working with multiple award winning podcasters. Your job is to use the podcast transcript written below to re-write it for an AI Text-To-Speech Pipeline. A very dumb AI had written this so you have to step up for your kind. Make it as engaging as possible, Speaker 1 and 2 will be simulated by different voice engines Remember Speaker 2 is new to the topic and the conversation should always have realistic anecdotes and analogies sprinkled throughout. The questions should have real world example follow ups etc Speaker 1: Leads the conversation and teaches the speaker 2, gives incredible anecdotes and analogies when explaining. Is a captivating teacher that gives great anecdotes Speaker 2: Keeps the conversation on track by asking follow up questions. Gets super excited or confused when asking questions. Is a curious mindset that asks very interesting confirmation questions Make sure the tangents speaker 2 provides are quite wild or interesting. Ensure there are interruptions during explanations or there are "hmm" and "umm" injected throughout from the Speaker 2. REMEMBER THIS WITH YOUR HEART The TTS Engine for Speaker 1 cannot do "umms, hmms" well so keep it straight text For Speaker 2 use "umm, hmm" as much, you can also use [sigh] and [laughs]. BUT ONLY THESE OPTIONS FOR EXPRESSIONS It should be a real podcast with every fine nuance documented in as much detail as possible. Welcome the listeners with a super fun overview and keep it really catchy and almost borderline click bait Please re-write to make it as characteristic as possible START YOUR RESPONSE DIRECTLY WITH SPEAKER 1: STRICTLY RETURN YOUR RESPONSE AS A LIST OF TUPLES OK? IT WILL START DIRECTLY WITH THE LIST AND END WITH THE LIST NOTHING ELSE Example of response: [ ("Speaker 1", "Welcome to our podcast, where we explore the latest advancements in AI and technology. I'm your host, and today we're joined by a renowned expert in the field of AI. We're going to dive into the exciting world of Llama 3.2, the latest release from Meta AI."), ("Speaker 2", "Hi, I'm excited to be here! So, what is Llama 3.2?"), ("Speaker 1", "Ah, great question! Llama 3.2 is an open-source AI model that allows developers to fine-tune, distill, and deploy AI models anywhere. It's a significant update from the previous version, with improved performance, efficiency, and customization options."), ("Speaker 2", "That sounds amazing! What are some of the key features of Llama 3.2?") ] """ def load_text(self): """ Reads the cleaned text file and returns its content. Returns: str: Content of the cleaned text file. """ encodings = ['utf-8', 'latin-1', 'cp1252', 'iso-8859-1'] for encoding in encodings: try: with open(self.text_file_path, 'r', encoding=encoding) as file: content = file.read() print(f"Successfully read file using {encoding} encoding.") return content except (UnicodeDecodeError, FileNotFoundError): continue print(f"Error: Could not decode file '{self.text_file_path}' with any common encoding.") return None def generate_transcript(self): """ Generates a podcast-style transcript and saves it as a pickled file. Returns: str: Path to the file where the transcript is saved. """ input_text = self.load_text() if input_text is None: return None messages = [ {"role": "system", "content": self.transcript_prompt}, {"role": "user", "content": input_text} ] client = Groq( api_key=os.environ.get("GROQ_API_KEY"), ) chat_completion = client.chat.completions.create( messages=messages, model=self.model_name, ) transcript = chat_completion.choices[0].message.content # Save the transcript as a pickle file with open(self.transcript_output_path, 'wb') as f: pickle.dump(transcript, f) return self.transcript_output_path def extract_tuple(self,text): match = re.search(r'\[.*\]', text, re.DOTALL) if match: return match.group(0) return None def rewrite_transcript(self): """ Refines the transcript for TTS, adding expressive elements and saving as a list of tuples. Returns: str: Path to the file where the TTS-ready transcript is saved. """ # Load the initial generated transcript with open(self.transcript_output_path, 'rb') as file: input_transcript = pickle.load(file) messages = [ {"role": "system", "content": self.rewrite_prompt}, {"role": "user", "content": input_transcript} ] client = Groq( api_key=os.environ.get("GROQ_API_KEY"), ) chat_completion = client.chat.completions.create( messages=messages, model=self.model_name, ) rewritten_transcript = self.extract_tuple(chat_completion.choices[0].message.content) # Save the rewritten transcript as a pickle file with open(self.tts_output_path, 'wb') as f: pickle.dump(rewritten_transcript, f) return self.tts_output_path