End of training

README.md

@@ -4,37 +4,37 @@ language:
 license: apache-2.0
 base_model: openai/whisper-tiny.en
 tags:
-- hf-asr-leaderboard
+- nyansapo_ai-asr-leaderboard
 - generated_from_trainer
 datasets:
-- eai6/bungoma_training
+- NyansapoAI/azure-dataset
 metrics:
 - wer
 model-index:
-- name: Whisper tiny
+- name: whisper-tiny.en
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Nyansapo AI Dataset
-      type: eai6/bungoma_training
-      args: 'config: en, split: test'
+      name: Azure-dataset
+      type: NyansapoAI/azure-dataset
+      args: 'split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 81.81818181818183
+      value: 44.34857635893012
 ---
 
 <!-- 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
+# whisper-tiny.en
 
-This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Nyansapo AI Dataset dataset.
+This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Azure-dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0310
-- Wer: 81.8182
+- Loss: 0.0680
+- Wer: 44.3486
 
 ## Model description
 
@@ -57,23 +57,19 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 1500
+- lr_scheduler_warmup_steps: 250
+- training_steps: 1000
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.695         | 3.11  | 250  | 1.2659          | 44.9495  |
-| 0.8192        | 6.21  | 500  | 0.0613          | 182.5253 |
-| 0.2123        | 9.32  | 750  | 0.0362          | 61.0101  |
-| 0.1294        | 12.42 | 1000 | 0.0336          | 39.1919  |
-| 0.1136        | 15.53 | 1250 | 0.0311          | 91.0101  |
-| 0.1042        | 18.63 | 1500 | 0.0310          | 81.8182  |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 1.2415        | 1.38  | 250  | 0.6131          | 26.6609 |
+| 0.3582        | 2.76  | 500  | 0.0882          | 43.0544 |
+| 0.2094        | 4.14  | 750  | 0.0723          | 43.6583 |
+| 0.1788        | 5.52  | 1000 | 0.0680          | 44.3486 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6409a933544bccf6be853db37c7e85a75a218ec9492388543c76752b03300e90
+oid sha256:411d4ed7ddae88912835d3b9b4b3737f4734699c4ef90c2f1ed7f5880d5ca996
 size 151060136

runs/Mar29_02-05-39_Edwards-MacBook-Pro-2.local/events.out.tfevents.1711692340.Edwards-MacBook-Pro-2.local.93542.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373d9ff1764ac2ff1ec405da9c25db1ad03acbab5a4733437f98c569cf69a1b5
-size 12736
+oid sha256:0c762955de809e4604b8683de8ecf5b6eed541cac8294f5bfa781fa02ff373b0
+size 15518