🤝 Top Collabolators
🤓 Submissions
ATLAS
Startups and venture capital firms have a lot of business system materials to define and generate. To name a few: -Create an LLC -Create articles of incorporation -Create an Operating Plan -Create a business plan -Conduct market analysis -Conduct Investment planning -Write up legal disclaimers, -Build a website landing page -Generate branding materials With ATLAS, you can reduce the amount of time it takes to build your startup’s business system materials from months to minutes. Signup, fill in the forms and let autonomous agents take care of the rest. Redirect more of your time toward developing and delivering the best product to your customers. ATLAS is an intuitively integrated autonomous agent system which uses Claude, OpenAI and llama_index. It performs searches based on a few target areas, including market analysis, investment prospects, scalability, sustainability and more. After the finalized data is generated, ATLAS will then generate the text and PDF for the document. Taking charge of business system materials generation, using data-driven AI, ATLAS generates exceptional business value for startups by freeing up more time (one of the most valuable assets for startup founders) and delivering valuable business system materials at a fraction of the traditional cost. There are currently no other apps which complete all of the business system materials generation tasks that ATLAS offers. ATLAS will transform the business system materials generation app space by functioning as an all-in-one solution to create the different business system materials required for a startup. Technology Tags: Anthropic Appwrite Astro cChardet ChatGPT ChromaDB FastAPI Fooocus Langchain Llama-hub Llama-index lxml Metaphor_python n8n Pydantic PyPDF R3f SentenceTransformers Svelte Trafilatura validators
LoFi Focus
## Implementation - Built as a Chrome browser extension for ease of use - Uses JavaScript content scripts to analyze webpages and play lofi audio - Leverages AudioCraft's MusicGen AI model to generate the lofi tracks - Polished UI allows easy control over the music generation --- ## Our Custom Model We collected a dataset of original non-copyright lofi music. This gave us access to a large corpus of high-quality training data without any copyright issues. We split the lofi songs into 30 second audio clips and paired each clip with a text prompt describing the mood, instruments, tempo and other qualities of that segment. Examples include "slow chill hip hop beat with mellow piano and vinyl crackle" and "upbeat lofi with energetic drums and warm bassline". We formatted this dataset into the required .wav and .txt file pairs that musicgen_trainer expects. The text prompts would guide the model to learn the nuances of lofi hip hop. We then ran musicgen_trainer on this dataset, configuring it to use the small architecture for optimization purposes. We trained for 100 epochs with a learning rate of 1e-5 and batch size of 4. During training, musicgen_trainer used the audio/text pairs to fine-tune MusicGen on lofi music. The pre-trained weights were specialized to generate high quality lofi given descriptive prompts. After training finished, we saved the best performing model checkpoint. We now have a MusicGen variant skilled at generating original lofi tunes according to textual descriptions. --- ## Why Download Our Chrome Extension - Improve focus and concentration when reading - Make reading more enjoyable and relaxing - Boost productivity - Avoid listening fatigue - Portability - Ease of use - Less anxiety - Nostalgia
shellie
Limitations in AI research and multimodal pipelines have limited possibilities with multimodal language translation and accessibility. Shellie democratizes access to knowledge with an open-source universal react component for universal speech translation. Features: Automatic speech recognition for nearly 100 languages Speech-to-text translation for nearly 100 input and output languages Speech-to-speech translation, supporting nearly 100 input languages and 35 (+ English) output languages Text-to-text translation for nearly 100 languages Text-to-speech translation, supporting nearly 100 input languages and 35 (+ English) output languages Implementation: Built as a React component widget Uses JavaScript to call Gradio API endpoints from Huggingface Huggingface Runs Inference on Multi-Modal SeamlessM4T Model UI returns text or audio file in one click
