Update README.md

README.md

@@ -1,19 +1,41 @@
----
-license: apache-2.0
-base_model: openai/whisper-small
-tags:
-- generated_from_trainer
-model-index:
-- name: whisper-small-ga2en-v3.2-r
-  results: []
----
+---
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- generated_from_trainer
+model-index:
+- name: whisper-small-ga2en-v3.2-r
+  results: []
+datasets:
+- ymoslem/IWSLT2023-GA-EN
+- ymoslem/FLEURS-GA-EN
+- ymoslem/BitesizeIrish-GA-EN
+- ymoslem/SpokenWords-GA-EN-MTed
+- ymoslem/Tatoeba-Speech-Irish
+- ymoslem/Wikimedia-Speech-Irish
+language:
+- ga
+- en
+metrics:
+- bleu
+- wer
+- chrf
+library_name: transformers
+---
 
 <!-- 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-small-ga2en-v3.2-r
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
+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 best model checkpoint (this version) based on ChrF is at step 2700, epoch 3.5433, and
+it achieves the following results on the evaluation set:
+- Loss: 1.4313
+- Bleu: 30.87
+- Chrf: 47.72
+- Wer: 64.2954
 
 ## Model description
 
@@ -29,6 +51,10 @@ More information needed
 
 ## Training procedure
 
+### Hardware
+
+1 NVIDIA A100-SXM4-80GB
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -41,9 +67,44 @@ The following hyperparameters were used during training:
 - training_steps: 3000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+|Step	|Training Loss	|Validation Loss	|Bleu	|Chrf	|Wer|
+|:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|
+|100	|2.311900	|1.773697	|9.20	|28.23	|120.486267|
+|200	|1.870000	|1.479052	|16.90	|33.01	|83.701036|
+|300	|1.627700	|1.372679	|20.33	|38.68	|84.061234|
+|400	|1.460400	|1.309611	|24.52	|40.37	|74.696083|
+|500	|1.336300	|1.283173	|20.35	|40.77	|86.537596|
+|600	|1.193300	|1.255632	|20.63	|41.37	|95.632598|
+|700	|1.015600	|1.251285	|21.24	|41.42	|82.170194|
+|800	|0.518300	|1.292586	|28.08	|44.76	|66.951824|
+|900	|0.467300	|1.329429	|25.16	|42.93	|76.316974|
+|1000	|0.438700	|1.330984	|28.29	|46.08	|67.672220|
+|1100	|0.403600	|1.300828	|27.43	|46.32	|68.977938|
+|1200	|0.379500	|1.323791	|30.02	|45.48	|63.800090|
+|1300	|0.337100	|1.327949	|30.40	|47.61	|61.999100|
+|1400	|0.288000	|1.359497	|28.13	|44.60	|66.501576|
+|1500	|0.265100	|1.355470	|26.58	|45.51	|71.319226|
+|1600	|0.100800	|1.400149	|26.19	|46.02	|72.985142|
+|1700	|0.092300	|1.383455	|24.83	|46.18	|77.532643|
+|1800	|0.103900	|1.404863	|22.19	|43.19	|88.743809|
+|1900	|0.090100	|1.402833	|29.73	|45.85	|66.186403|
+|2000	|0.084200	|1.418717	|28.18	|45.29	|73.570464|
+|2100	|0.074800	|1.461650	|26.58	|44.66	|74.020711|
+|2200	|0.072000	|1.400547	|31.01	|47.30	|61.143629|
+|2300	|0.042900	|1.424147	|28.72	|45.53	|65.511031|
+|2400	|0.025200	|1.412174	|27.18	|47.19	|74.020711|
+|2500	|0.026500	|1.438945	|30.01	|46.73	|65.105808|
+|2600	|0.023300	|1.454140	|30.93	|46.65	|62.404322|
+|2700	|0.021600	|1.431275	|30.87	|47.72	|64.295362|
+|2800	|0.019200	|1.439022	|30.50	|46.98	|65.150833|
+|2900	|0.018200	|1.439916	|31.09	|47.27	|63.529941|
+|3000	|0.019000	|1.444545	|30.83	|47.35	|64.205313|
+
 ### Framework versions
 
 - Transformers 4.40.2
 - Pytorch 2.2.0+cu121
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1