Model Detail

CrisperWhisper2.0_large is an audio model with 772M parameters released by nyralabs. The model is registered under the automatic-speech-recognition pipeline tag on Hugging Face, distributed under a other license.

CrisperWhisper2.0_large ships with 772M parameters. Total weight footprint is approximately 1.5 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.

CrisperWhisper2.0_large is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.