Model save

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
-base_model: giigii91/whisper-tiny_v2.1-ro
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 datasets:
-- common_voice_11_0
+- common_voice_17_0
 model-index:
 - name: whisper-tiny_v2.2-ro
   results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny_v2.2-ro
 
-This model is a fine-tuned version of [giigii91/whisper-tiny_v2.1-ro](https://huggingface.co/giigii91/whisper-tiny_v2.1-ro) on the common_voice_11_0 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_17_0 dataset.
 
 ## Model description
 
@@ -36,14 +36,14 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 32
-- eval_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- training_steps: 20000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "giigii91/whisper-tiny_v2.1-ro",
+  "_name_or_path": "openai/whisper-tiny",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0434268de4226ad9ae2b1b39860c2f25db0062fc7499b2a5bcf720b5f7f4500d
+oid sha256:7ebd0e69e78190ffe1438491fa05cc1f5c1aa3a4c4db3bc1723adbb551ea2395
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1eb49342992f514d09176e6bd2877bb2b24c926414207c7ffb8b51be5e6254
+oid sha256:7d26766dcdc9e5f97b5c0b82aa95c120d7652aa62c77f668347468e183be384e
 size 5240