End of training

README.md

@@ -9,19 +9,19 @@ tags:
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny English - G.Mehdi
+- name: Whisper Tiny English v2
   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 English - G.Mehdi
+# Whisper Tiny English v2
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the commands_dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0019
-- Wer: 2.8333
+- Loss: 0.0003
+- Wer: 3.3333
 
 ## Model description
 
@@ -46,16 +46,18 @@ 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: 10
-- training_steps: 100
+- lr_scheduler_warmup_steps: 30
+- training_steps: 300
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.0075        | 1.0   | 75   | 0.0026          | 3.0833 |
-| 0.0027        | 1.33  | 100  | 0.0019          | 2.8333 |
+| 0.0098        | 1.0   | 75   | 0.0038          | 3.3333 |
+| 0.0035        | 2.0   | 150  | 0.0006          | 3.75   |
+| 0.0031        | 3.0   | 225  | 0.0004          | 3.1667 |
+| 0.0012        | 4.0   | 300  | 0.0003          | 3.3333 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6d4abef2d1a4443a96fc1557f50e0f5df55392c3f07e779c0e456b38879cf7
+oid sha256:589f6477a53eea5ce7569c1e7a1e52be608816f3ce54d9fa980b77d5f1d44f7b
 size 151061672

runs/Jan28_18-22-21_a61240245982/events.out.tfevents.1706466701.a61240245982.31707.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c376052daa4444429c292d7e36f4d0e34951aae1692e81bd85901027acdcab
+size 8696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffce619566d6c2c0e4a0581d270e8c95e1f2a62860fbd1e26947613543be33b
+oid sha256:b79aa00fd5b70cbec5a90b93ccde879f7dffd4516a86dd90e9bc692502476cb4
 size 4856