The ggml-medium.bin file typically requires roughly 1.5 GiB of storage.
OpenAI released Whisper, a state-of-the-art automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitasking web data. Whisper was released in several sizes: (~39 Million Parameters) Base (~74 Million Parameters) Small (~244 Million Parameters) Medium (~769 Million Parameters) Large (~1.55 Billion Parameters) ggml-medium.bin
High accuracy . It handles complex formatting, multiple speakers, overlapping audio, and multi-language translation smoothly while remaining fast enough for consumer rigs. The ggml-medium
ggml-medium-q5_0.bin : A quantized (compressed) version that reduces file size and memory usage by approximately 50% with minimal loss in accuracy. How to Use It ggml-medium.bin