NbAiLab
/

whisper-small-nob

Automatic Speech Recognition

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

pere commited on Dec 16, 2022

Commit

00df1af

·

1 Parent(s): bc7aef5

readme

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ model-index:
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) trained on several datasets.
-It is currently in the middle of a large training. Currently achieves the following results on the evaluation set:
 - Loss: 0.4780
 - Wer: 23.93
@@ -58,9 +58,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 1000
 - training_steps: 50.000 (currently @1.000)
 - mixed_precision_training: fp16
-- deepspee: true
-### Training results
 See [Tensorboad Metrics](https://huggingface.co/NbAiLab/whisper-small-nob/tensorboard)

 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) trained on several datasets.
+It is currently in the middle of a large training. Currently it achieves the following results on the evaluation set:
 - Loss: 0.4780
 - Wer: 23.93
 - lr_scheduler_warmup_steps: 1000
 - training_steps: 50.000 (currently @1.000)
 - mixed_precision_training: fp16
+- deepspeed: true
+### Live Training results
 See [Tensorboad Metrics](https://huggingface.co/NbAiLab/whisper-small-nob/tensorboard)