Moonshine-MN Phase 1 (Mongolian ASR)

This is a fine-tuned Moonshine model for Mongolian Automatic Speech Recognition (ASR).

Evaluation Results

At Step 5000 (Epoch ~12.23), the model achieved the following results on the evaluation set:

  • Eval Loss: 6.8991
  • Eval WER (Word Error Rate): 87.86
  • Eval Runtime: 249.5884
  • Eval Samples per Second: 16.119
  • Eval Steps per Second: 2.015
Downloads last month
5
Safetensors
Model size
27.1M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Batuka0901/moonshine-mn-v1