End of training

README.md

@@ -6,6 +6,8 @@ base_model: openai/whisper-base
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
+datasets:
+- common_voice_16_1
 model-index:
 - name: ft_model
   results: []
@@ -17,6 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 # ft_model
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6109
+- Cer: 16.9926
 
 ## Model description
 
@@ -37,7 +42,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,6 +52,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Cer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.3246        | 0.25  | 500  | 0.6696          | 18.6400 |
+| 0.3243        | 0.5   | 1000 | 0.6509          | 18.5784 |
+| 0.2622        | 0.75  | 1500 | 0.6245          | 17.5366 |
+| 0.3307        | 1.0   | 2000 | 0.6109          | 16.9926 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d4cb1a73ec954bbb25ff5545315b740b59ddcfd7276b15a7349e4b79c33aae
+oid sha256:f95abef804b461f2985aebe19729df8346fbe21591aafcbbc2f1345cc84f1eb7
 size 290403936

runs/Jan22_12-32-02_309b06cb0fe7/events.out.tfevents.1705926731.309b06cb0fe7.753.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4824d60ac459bad3e2590567667675a078bd1ec82fcc2a9c668422cdccad37
-size 15531
+oid sha256:d79051792e39c3c461b8d2efa6075ec2f41d5222ab3ef090563ecf68b733485b
+size 19343