Automatic Speech Recognition Speech To Text
Automatic-Speech-Recognition-Speech-to-Text
Automatic-Speech-Recognition-Speech-to-Text
Transcribe Persian audio to text
Demo of Persian ASR model trained on CV17, YouTube, In House
Trained on 800 hours (CV17, YouTube, NasleMana, In house)
Fine-tuned SpeechT5 for ASR on Farsi language
A speech-to-text arena to compare multiple ASR models
An Agentic Framework with Tools for Complex Reasoning
LLM + Langchain + Speciality
Process and analyze documents
Extract and visualize knowledge graphs from any text
Generate Podcast using Kokoro-TTS!
Efficient, fast, and natural text to speech with StyleTTS 2!
See, read, and reasonβbetter together.
Generate detailed reports on any topic
Summarize text using a pre-trained model