carlot/whisper-base-basewhisper_mixed_v1

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: openai/whisper-base
 tags:
 - generated_from_trainer
 datasets:
@@ -15,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-base-mixed_basewhisper_v1.1
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the audiofolder dataset.
+This model was trained from scratch on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3770
-- Cer: 16.3142
+- Loss: 0.0000
+- Cer: 47.2222
 
 ## Model description
 
@@ -49,12 +47,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0003        | 125.0 | 1000 | 0.3509          | 17.3212 |
-| 0.0001        | 250.0 | 2000 | 0.3665          | 16.8177 |
-| 0.0001        | 375.0 | 3000 | 0.3740          | 16.6163 |
-| 0.0001        | 500.0 | 4000 | 0.3770          | 16.3142 |
+| Training Loss | Epoch  | Step | Validation Loss | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0           | 1000.0 | 1000 | 0.0000          | 69.4444 |
+| 0.0           | 2000.0 | 2000 | 0.0000          | 44.4444 |
+| 0.0           | 3000.0 | 3000 | 0.0000          | 47.2222 |
+| 0.0           | 4000.0 | 4000 | 0.0000          | 47.2222 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0e4b4eed4b303ed256afb99282aa6d5482fba87c0ed100b7cf63a7729b15b8
+oid sha256:c1b4f265a4c00946a06ed8d5a06ed59c43f2c43bec932575d6f623310afcdfd1
 size 290403936