Abstract: This paper proposes a novel meta-transfer learning method to improve automatic speech recognition (ASR) performance in low-resource languages. Nowadays, we are witnessing high interest in ...
The company stated that the model has been trained on proprietary multilingual datasets spanning more than 1,056 domains.
Gnani.ai launches Vachana STT, a foundational Indic speech-to-text model trained on 1M hours, under the IndiaAI Mission to ...
New York, NY, Dec. 18, 2025 (GLOBE NEWSWIRE) -- Voximplant, a leading cloud communications platform, announced native support ...
Credit: Shutterstock Today marks an exciting moment for the developer community as xAI officially introduces the Grok Voice ...
This repo provides a command-line tool for performing automatic speech-to-text tasks (i.e., "transcription") using open source models from Hugging Face Hub. For interactive tasks, it allows users to ...
Obsessing over model version matters less than workflow.
What if you could transform hours of audio into precise, actionable text with just a few lines of code? In 2025, this is no longer a futuristic dream but a reality powered by innovative speech-to-text ...
An ESP32 client that captures audio over I2S and posts WAV to a server. A lightweight Flask/Gunicorn server that returns JSON transcriptions via speech_recognition. Designed for deterministic embedded ...
Abstract: This letter presents a new target speech recognition problem, where the target speech is defined by a keyword. For instance, when a person speaks “Hey Google” or “Help Me”, we hope the model ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback