x.comthreadMuhammad Waris (@WarisCodes) on X
Nemotron 3.5 Transcribe is a free open-weight speech-to-text model from NVIDIA covering 40 languages, including mixed-language speech. The post says it ties for first among open models with a 2.8% error rate. It says the model needs a large GPU such as an H100 or RTX 5090, so it will not run on a laptop. The post gives no benchmark name or model card link.
TL;DR Tweet announcing NVIDIA's open-weight Nemotron 3.5 Transcribe, a 40-language speech-to-text model with a 2.8% error rate that needs a large GPU.
Organisations named here
- NVIDIA
- Nemotron
Technologies named here
- Nemotron 3.5 Transcribe
Related in models
