End of training

README.md

@@ -1,40 +1,24 @@
 ---
-language:
-- ro
 license: apache-2.0
 base_model: openai/whisper-medium
 tags:
-- hf-asr-leaderboard
 - generated_from_trainer
-datasets:
-- mozilla-foundation/common_voice_16_1
 metrics:
 - wer
 model-index:
-- name: Whisper Medium Ro - Sarbu Vlad
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 16.1
-      type: mozilla-foundation/common_voice_16_1
-      args: 'config: ro, split: test'
-    metrics:
-    - name: Wer
-      type: wer
-      value: 12.045860180899657
+- name: Whisper_medium_ro_VladS_02_16_24_1500_steps_multi_gpu
+  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 Medium Ro - Sarbu Vlad
+# Whisper_medium_ro_VladS_02_16_24_1500_steps_multi_gpu
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 16.1 dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1622
-- Wer: 12.0459
+- Loss: 0.1471
+- Wer: 12.4512
 
 ## Model description
 
@@ -63,22 +47,20 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 250
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1565        | 0.98  | 250  | 0.1549          | 14.7079 |
-| 0.0939        | 1.96  | 500  | 0.1300          | 12.9443 |
-| 0.0427        | 2.94  | 750  | 0.1298          | 11.9854 |
-| 0.0245        | 3.92  | 1000 | 0.1357          | 12.2485 |
-| 0.0147        | 4.9   | 1250 | 0.1425          | 11.9823 |
-| 0.0084        | 5.88  | 1500 | 0.1543          | 12.1154 |
-| 0.0054        | 6.86  | 1750 | 0.1599          | 11.9763 |
-| 0.0043        | 7.84  | 2000 | 0.1622          | 12.0459 |
+| 0.3367        | 0.98  | 250  | 0.1873          | 16.5290 |
+| 0.1131        | 1.96  | 500  | 0.1383          | 13.7792 |
+| 0.0597        | 2.94  | 750  | 0.1306          | 12.3695 |
+| 0.0311        | 3.92  | 1000 | 0.1329          | 12.2758 |
+| 0.0168        | 4.9   | 1250 | 0.1410          | 12.5117 |
+| 0.0102        | 5.88  | 1500 | 0.1471          | 12.4512 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:844686a7ccf2f23fdee2f07271cca8e479e8bcec77bebbd7068ccfb32bb9fdb0
+oid sha256:e75006a52a5a5f170ea6e54a4e4d6431875264025c08061828f97cda91496e77
 size 1634047376

runs/Feb16_14-31-01_ubuntu-llama/events.out.tfevents.1708086674.ubuntu-llama.697324.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63878bdab2194cd22f65957b1c91421af5e06baac6ecae15c51647cf6921de83
-size 16608
+oid sha256:1cdff35752cebc4343c96c153a31e4257cba82e5d499115a2b54367fe63774fc
+size 16962