End of training

README.md

@@ -19,8 +19,8 @@ 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 Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3744
-- Cer: 29.0803
+- Loss: 0.6474
+- Cer: 48.6382
 
 ## Model description
 
@@ -52,15 +52,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.6757        | 0.6452 | 1000 | 0.6165          | 43.3161 |
-| 0.3539        | 1.2903 | 2000 | 0.4712          | 34.8316 |
-| 0.2883        | 1.9355 | 3000 | 0.4036          | 31.2306 |
-| 0.1566        | 2.5806 | 4000 | 0.3744          | 29.0803 |
+| 0.9789        | 0.6452 | 1000 | 0.9021          | 60.2169 |
+| 0.61          | 1.2903 | 2000 | 0.7536          | 53.3884 |
+| 0.5611        | 1.9355 | 3000 | 0.6703          | 51.3360 |
+| 0.3359        | 2.5806 | 4000 | 0.6474          | 48.6382 |
 
 
 ### Framework versions
 
-- Transformers 4.40.0
+- Transformers 4.40.1
 - Pytorch 2.1.2
-- Datasets 2.18.0
+- Datasets 2.19.0
 - Tokenizers 0.19.1

generation_config.json

@@ -262,5 +262,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.40.1"
 }

runs/Apr25_15-20-05_fb1d78a8eadd/events.out.tfevents.1714058406.fb1d78a8eadd.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79c5b4aded1ec24ba3ae4f7c921193df7767854965771d2dfa485a4f9184239
-size 40533
+oid sha256:c2071609b19a739730a4603bd39a48e2e582604f78a42caca52b2b1a38d2c262
+size 46373