Canary-Qwen-2.5B - Fine-tuned on Children's Speech
Fine-tuned from nvidia/canary-qwen-2.5b on children's speech data from the DrivenData ASR competition.
Training config
- Mode: full
- Max steps: 7900
- Batch size: 12 (grad_acc: 4)
- Learning rate: 3e-05
- Fine-tuning: full (all parameters)
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support