Model Detail

SoulX-Transcriber is an audio model with 17.6B parameters released by Soul-AILab. The model is registered under the automatic-speech-recognition pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.

SoulX-Transcriber ships with 17.6B parameters. Total weight footprint is approximately 35.3 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

SoulX-Transcriber 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.