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:
-- VladS159/common_voice_romanian_speech_synthesis
 metrics:
 - wer
 model-index:
-- name: Whisper Medium Ro - Sarbu Vlad - multi gpu
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 16.1 + Romanian speech synthesis
-      type: VladS159/common_voice_romanian_speech_synthesis
-      args: 'config: ro, split: test'
-    metrics:
-    - name: Wer
-      type: wer
-      value: 12.181988686208669
+- name: Whisper_medium_ro_VladS_1000_steps_multi_gpu_25_02_2024
+  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 - multi gpu
+# Whisper_medium_ro_VladS_1000_steps_multi_gpu_25_02_2024
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 16.1 + Romanian speech synthesis 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: 0.1620
-- Wer: 12.1820
+- Loss: 0.1247
+- Wer: 11.7262
 
 ## Model description
 
@@ -54,31 +38,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 3
-- total_train_batch_size: 48
-- total_eval_batch_size: 48
+- total_train_batch_size: 30
+- total_eval_batch_size: 30
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 200
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.148         | 0.98  | 250  | 0.1494          | 14.1574 |
-| 0.0875        | 1.96  | 500  | 0.1295          | 12.9080 |
-| 0.0404        | 2.94  | 750  | 0.1285          | 11.8734 |
-| 0.0227        | 3.92  | 1000 | 0.1353          | 12.1094 |
-| 0.0139        | 4.9   | 1250 | 0.1409          | 11.9702 |
-| 0.0076        | 5.88  | 1500 | 0.1539          | 12.0459 |
-| 0.005         | 6.86  | 1750 | 0.1599          | 12.1880 |
-| 0.0039        | 7.84  | 2000 | 0.1620          | 12.1820 |
+| 0.1447        | 0.61  | 250  | 0.1532          | 13.8768 |
+| 0.0599        | 1.23  | 500  | 0.1305          | 12.5141 |
+| 0.0595        | 1.84  | 750  | 0.1256          | 12.3255 |
+| 0.032         | 2.46  | 1000 | 0.1247          | 11.7262 |
 
 
 ### Framework versions

runs/Feb25_02-35-41_ubuntu-llama/events.out.tfevents.1708821359.ubuntu-llama.190234.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f0e95684a4b52f91c28b9fe61e1c29bd3efcb11cd6573cddbccda45f47342b
-size 12879
+oid sha256:197d474c749403d0a77b39c43c2c810061718fb78382575721f9c68ddbf888cf
+size 13233