End of training

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- hi
+- ro
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
@@ -21,11 +21,11 @@ model-index:
       type: mozilla-foundation/common_voice_11_0
       config: ro
       split: test
-      args: 'config: hi, split: test'
+      args: 'config: ro, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 39.75912251774321
+      value: 42.218080149114634
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Romanian voice 1.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2590
-- Wer: 39.7591
+- Loss: 0.3430
+- Wer: 42.2181
 
 ## Model description
 
@@ -55,12 +55,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-07
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 250
@@ -71,14 +69,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1607        | 0.9   | 500  | 0.2686          | 33.4540 |
-| 0.1676        | 1.8   | 1000 | 0.2659          | 34.7265 |
-| 0.1535        | 2.7   | 1500 | 0.2633          | 35.5975 |
-| 0.1633        | 3.6   | 2000 | 0.2616          | 37.0994 |
-| 0.1626        | 4.5   | 2500 | 0.2605          | 39.0530 |
-| 0.1597        | 5.4   | 3000 | 0.2596          | 39.0745 |
-| 0.1509        | 6.29  | 3500 | 0.2592          | 39.9276 |
-| 0.1504        | 7.19  | 4000 | 0.2590          | 39.7591 |
+| 0.396         | 0.9   | 1000 | 0.5565          | 88.6587 |
+| 0.187         | 1.8   | 2000 | 0.4436          | 53.4841 |
+| 0.0744        | 2.7   | 3000 | 0.3862          | 53.7279 |
+| 0.0222        | 3.6   | 4000 | 0.3430          | 42.2181 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a85334fdf70d6db8e938a6cbac4f2198e149d5385e4ea6a01d402f730867d9
+oid sha256:9add346e1ce142facf6af8eb1f24c7013ca8ea5052e61b212eb06bee34af46c9
 size 966995080

runs/Dec06_21-56-04_ArtanisPC/events.out.tfevents.1701896174.ArtanisPC.786.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75de8edfb502180760480ba06b492b895a4890f775d6a8a93cafe868f453d11
+size 6565

runs/Dec06_22-14-55_ArtanisPC/events.out.tfevents.1701897302.ArtanisPC.786.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fabab1237da4d2d20971e4c017243ef2d42d65e2cef17731e38b7334fcd9516
+size 15525

runs/Dec06_23-37-57_ArtanisPC/events.out.tfevents.1701902281.ArtanisPC.786.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0374a93c3ebe3027d5ea7a4f49786cece933e7bf097f19601b6aefe87e5c74e
+size 31899

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81017dde990bdc0e2ebfd334523bac9853caa7fb66ccddc42b9420ca7dd0c150
+oid sha256:6c85cdc5000db92b6c5323f03fede29c47df56f7dfcc85d346d0940a16138f88
 size 4856