End of training

README.md

@@ -1,24 +1,25 @@
 ---
 library_name: transformers
-language:
-- aka
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
-datasets:
-- akan_voice_v2
+metrics:
+- wer
 model-index:
-- name: Whisper-tiny-100-Akan-Kaku
+- name: whisper-tiny-akan
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper-tiny-100-Akan-Kaku
+# whisper-tiny-akan
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Akan Dataset v2 dataset.
+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: 0.9606
+- Wer: 70.5282
 
 ## Model description
 
@@ -43,12 +44,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 20
-- training_steps: 20
+- lr_scheduler_warmup_steps: 200
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.2351        | 11.6279 | 1000 | 0.8391          | 67.0857 |
+| 0.0976        | 23.2558 | 2000 | 0.9606          | 70.5282 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bce40b872a77fc371c72f66ab0e985920d01197679b08aeda34e5449b112007
+oid sha256:7fbd1cca7a5c808228e952186b47ae68153d5da31ef8d7351dc7a3427ba6b444
 size 151061672