faster-whisper-small-int8 is an optimized, INT8-quantized version of the OpenAI Whisper small model for speech-to-text. Created by the Rhasspy team, it is designed for efficient local inference with significantly reduced memory usage and faster performance while maintaining good transcription accuracy. It is available on Hugging Face for use with Transformers or faster-whisper libraries.
In the Other AI space, Faster Whisper Small takes a focused approach. It focuses on running fast, accurate, and memory-efficient automatic speech recognition locally. It is built as an open-source project for developers. Faster Whisper Small is open source under the Open Source license. It runs on the web and API.
Rhasspy builds and maintains Faster Whisper Small, and the product first shipped in 2023. Key capabilities include Speech Recognition, INT8 Quantization, and Fast Inference.
Latest indexed changes and source events
rhasspy/faster-whisper-small-int8 verified by the PulseGate indexer
Other apps tracked under the same category.
