Update README.md

README.md

@@ -16,6 +16,7 @@ datasets:
 metrics:
 - bleu
 - wer
+- chrf
 model-index:
 - name: Whisper Small GA-EN Speech Translation
   results:
@@ -23,7 +24,9 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia + augmented
+      name: >-
+        IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia +
+        augmented
       type: ymoslem/IWSLT2023-GA-EN
     metrics:
     - name: Bleu
@@ -32,6 +35,7 @@ model-index:
     - name: Wer
       type: wer
       value: 71.49932462854571
+library_name: transformers
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -39,12 +43,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small GA-EN Speech Translation
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia + augmented dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3512
-- Bleu: 30.11
-- Chrf: 46.73
-- Wer: 71.4993
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small)
+on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia datasets.
+The datasets are augmented in two ways: noise augmentation, and truncating low-amplitude samples.
+The best model checkpoint (this version) based on ChrF is at step 2800, epoch 1.2259, and
+it achieves the following results on the evaluation set:
+- Loss: 1.3547
+- Bleu: 32.57
+- Chrf: 47.04
+- Wer: 62.0891
 
 ## Model description
 
@@ -60,6 +67,10 @@ More information needed
 
 ## Training procedure
 
+### Hardware
+
+1 NVIDIA A100-SXM4-80GB
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -69,8 +80,10 @@ 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: 0
 - training_steps: 3000
 - mixed_precision_training: Native AMP
+- generation_max_length: 225
 
 ### Training results
 
@@ -113,4 +126,4 @@ The following hyperparameters were used during training:
 - Transformers 4.40.2
 - Pytorch 2.2.0+cu121
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1