Instructions to use Reza2kn/visualears-xlsr-300m-v2-cont-step1568 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reza2kn/visualears-xlsr-300m-v2-cont-step1568 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Reza2kn/visualears-xlsr-300m-v2-cont-step1568")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Reza2kn/visualears-xlsr-300m-v2-cont-step1568") model = AutoModelForCTC.from_pretrained("Reza2kn/visualears-xlsr-300m-v2-cont-step1568") - Notebooks
- Google Colab
- Kaggle
VisualEars XLS-R 300M v2 continuation step 1568
Final continuation checkpoint from /workspace/visualears_train/runs/visualears_v2_cont_from_ckpt1000_single_b24ga4_20260608T050121Z.
Training lineage:
- Continued from DDP checkpoint-1000 of
visualears_v2_decode_gated_alltiers_equal_headkeep_tokfix_b12ga4_ddpsafe_20260608T021656Z. - Single-GPU continuation: batch 24, grad accumulation 4, LR 4e-6, max_steps 568.
Double eval already run before upload:
- Gold-69 WER: 27.69%, CER: 9.62%
- FLEURS fa_ir test WER: 19.15%, CER: 5.84%
model.safetensors SHA256: 085fca58e419e4860d0435b0e31f4d7f484ff2f033915406cf7bf930791e3028
- Downloads last month
- 77