Model save

README.md

@@ -16,14 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-tiny_v2.1-ro
 
 This model is a fine-tuned version of [giigii91/whisper-tiny_v2.2-ro](https://huggingface.co/giigii91/whisper-tiny_v2.2-ro) on the common_voice_11_0 dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.6708
-- eval_wer: 251.1146
-- eval_runtime: 1222.963
-- eval_samples_per_second: 3.155
-- eval_steps_per_second: 0.395
-- epoch: 0.3597
-- step: 100
 
 ## Model description
 
@@ -43,14 +35,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
+- lr_scheduler_warmup_steps: 500
 - training_steps: 5000
 - mixed_precision_training: Native AMP
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeced6ac7f06cacf9e74b7e19ee40b40a94f274aaed3c58ff28246d568bdfb0e
+oid sha256:1c674250c0627ee0c3bd006f4a245073ccd3751e0e87b3e7f8da160a1af00e45
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b56b74820e0bcb15ab866da98c0564397e9f1679c07ece8b4edbe36e45a8ec
+oid sha256:c7a7ea58c115abd81b71e68151ff4a1f35406a3731036d4724d2d1e64ed7b84b
 size 5240