From 9057ba478e735492dc789db105e7c9bce3bb8ae5 Mon Sep 17 00:00:00 2001 From: Sanyam Bhutani <sanyambhutani@meta.com> Date: Fri, 25 Oct 2024 14:58:00 -0700 Subject: [PATCH] Update recipes/quickstart/NotebookLlama/README.md Co-authored-by: Hamid Shojanazeri <hamid.nazeri2010@gmail.com> --- recipes/quickstart/NotebookLlama/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/recipes/quickstart/NotebookLlama/README.md b/recipes/quickstart/NotebookLlama/README.md index 1dea1835..55736f26 100644 --- a/recipes/quickstart/NotebookLlama/README.md +++ b/recipes/quickstart/NotebookLlama/README.md @@ -12,7 +12,7 @@ It assumes zero knowledge of LLMs, prompting and audio models, everything is cov Here is step by step thought (pun intended) for the task: -- Step 1: Pre-process PDF: Use `Llama-3.2-1B` to pre-process and save a PDF +- Step 1: Pre-process PDF: Use `Llama-3.2-1B` to pre-process the PDF and save it in a `.txt` file. - Step 2: Transcript Writer: Use `Llama-3.1-70B` model to write a podcast transcript from the text - Step 3: Dramatic Re-Writer: Use `Llama-3.1-8B` model to make the transcript more dramatic - Step 4: Text-To-Speech Workflow: Use `parler-tts/parler-tts-mini-v1` and `bark/suno` to generate a conversational podcast -- GitLab