End of training

README.md

@@ -7,17 +7,33 @@ tags:
 - generated_from_trainer
 datasets:
 - velocity-whisper-tiny
+metrics:
+- wer
 model-index:
-- name: whisper-small-finetuned-hinglish
-  results: []
+- name: whisper-tiny-finetuned-hinglish
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: whisper-training
+      type: velocity-whisper-tiny
+      args: 'config: hi, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 10.60473269062226
 ---
 
 <!-- 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-small-finetuned-hinglish
+# whisper-tiny-finetuned-hinglish
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the whisper-training dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0702
+- Wer: 10.6047
 
 ## Model description
 
@@ -43,11 +59,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- num_epochs: 40
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.001         | 17.8571 | 1000 | 0.0647          | 10.4294 |
+| 0.0003        | 35.7143 | 2000 | 0.0702          | 10.6047 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266a1d807ca0f4e12fa6a4dfbd297d3198b69fb1bb5dc7f437b0fd159ea2b7a9
+oid sha256:d805c3307077b3652c2ff434d9975c080843090954b9566adbdb1d48f679484b
 size 151061672

runs/Jun05_12-12-41_cd7e4c04dfb4/events.out.tfevents.1717589563.cd7e4c04dfb4.2238.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b548649ee7151f6082bd88d09178cb688d10c6aeda4aafdbffde457b40740258
-size 24133
+oid sha256:cdfb2b84973d3e6bfaac214edc6b6bf8177299282f403e0c81d86d5e1cd9fad1
+size 26386