Model save

README.md

@@ -2,6 +2,8 @@
 library_name: transformers
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: t5-asr-CV16
   results: []
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # t5-asr-CV16
 
 This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6678
+- Wer: 0.7639
 
 ## Model description
 
@@ -35,12 +40,28 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 64
-- total_train_batch_size: 2048
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 4096
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:------:|
+| 1.8105        | 1.9694  | 48   | 0.7812          | 0.8528 |
+| 1.6752        | 3.9694  | 96   | 0.7174          | 0.8285 |
+| 1.6146        | 5.9694  | 144  | 0.7357          | 0.8215 |
+| 1.3847        | 7.9694  | 192  | 0.6796          | 0.8172 |
+| 1.2792        | 9.9694  | 240  | 0.6601          | 0.7841 |
+| 1.2129        | 11.9694 | 288  | 0.6540          | 0.7764 |
+| 1.279         | 13.9694 | 336  | 0.6792          | 0.7837 |
+| 1.1706        | 15.9694 | 384  | 0.6695          | 0.7888 |
+| 1.0348        | 17.9694 | 432  | 0.6931          | 0.7948 |
+| 0.9335        | 19.9694 | 480  | 0.6678          | 0.7639 |
+
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7009eba43dab853275318918f24e9c9dc313e11586cf68b61fb217abbc3b4f35
+oid sha256:b6dd7a4023ed5c1316d6c79ca364ee2b68072747a3c0d5de3e8794dca101784a
 size 1226432312