Edit model card
README.md exists but content is empty.
Use the Edit model card button to edit it.
Source link
Edit model card
WhisperSpeech
Progress update [2024-01-18]
Progress update [2024-01-10]
Progress update [2023-12-10]
Downloads
Roadmap
Architecture
Whisper for modeling semantic tokens
EnCodec for modeling acoustic tokens
Appreciation
Consulting
Citations
WhisperSpeech
If you have questions or you want to help you can find us in the
#audio-generation channel on the LAION Discord server.
An…
Start up Profile Bewgle Inc. is a customer review analysis technology company. It helps online retailers, app developers, etc. analyse natural language reviews written by customers. Bewgle uses cutting-edge AI and Machine Learning to help brands and e-commerce companies to collect, understand and leverage customer reviews. It generates insights from reviews enabling e-commerce product…
Apple and Disney will have to include shareholder votes regarding their use of artificial intelligence (AI) in their upcoming annual meetings, as ruled by the US Securities and Exchange Commission (SEC). The requests made by both companies to exclude these calls for reports on AI usage were rejected by the SEC. The use of AI…
Google supercharged its search engine with generative AI capabilities in May 2023. Since then, the company has been introducing more generative AI-based features and experiences for its users worldwide. Available for limited users, Google is fundamentally changing the way we use search engines with the power of artificial intelligence.
Google has now added a host…
DistilRoberta-financial-sentiment
This model is a fine-tuned version of distilroberta-base on the financial_phrasebank dataset.
It achieves the following results on the evaluation set:
Loss: 0.1116
Accuracy: 0.9823
Base Model description
This model is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT.
The code for the distillation process can…
HelpingAI-Vision
Model details
The fundamental concept behind HelpingAI-Vision is to generate one token embedding per N parts of an image, as opposed to producing N visual token embeddings for the entire image. This approach, based on the HelpingAI-Lite and incorporating the LLaVA adapter, aims to enhance scene understanding by capturing…
LayoutLM for Invoices
This is a fine-tuned version of the multi-modal LayoutLM model for the task of question answering on invoices and other documents. It has been fine-tuned on a proprietary dataset of
invoices as well as both SQuAD2.0 and DocVQA for general comprehension.
Non-consecutive tokens
Unlike other QA models, which can only…