End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4574
-- Wer: 1.4939
+- Loss: 1.2487
+- Wer: 1.3242
 
 ## Model description
 
@@ -45,21 +45,17 @@ The following hyperparameters were used during training:
 - 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: 2
-- training_steps: 8
+- lr_scheduler_warmup_steps: 80
+- training_steps: 800
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 0.0   | 1    | 3.0351          | 1.4989 |
-| 3.6663        | 0.01  | 2    | 2.8513          | 1.5283 |
-| 3.6663        | 0.01  | 3    | 2.6387          | 1.4964 |
-| 3.6138        | 0.01  | 4    | 2.5656          | 1.5394 |
-| 3.6138        | 0.01  | 5    | 2.5272          | 1.5169 |
-| 3.1887        | 0.02  | 6    | 2.4940          | 1.5016 |
-| 3.1887        | 0.02  | 7    | 2.4701          | 1.4778 |
-| 3.052         | 0.02  | 8    | 2.4574          | 1.4939 |
+| 1.4242        | 0.51  | 200  | 1.4528          | 1.1595 |
+| 1.2641        | 1.01  | 400  | 1.3215          | 1.3512 |
+| 1.1987        | 1.52  | 600  | 1.2649          | 1.2247 |
+| 1.1687        | 2.03  | 800  | 1.2487          | 1.3242 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7591b4ea34f8a307db3ca5ec732f87d420559d224e2a02cb36705877e4f16416
+oid sha256:7565ab3670657a706995880d43bd7e3997543ce7523589e7a152cd51ca00bc46
 size 151096745