Update README.md

README.md

@@ -7,6 +7,9 @@ tags:
 - generated_from_trainer
 datasets:
 - espnet/yodas
+- google/fleurs
+- Sagicc/audio-lmb-ds
+- mozilla-foundation/common_voice_16_1
 metrics:
 - wer
 model-index:
@@ -16,8 +19,8 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Yodas
-      type: espnet/yodas
+      name: Common Voice 16_1
+      type: mozilla-foundation/common_voice_16_1
       config: sr
       split: test
       args: sr
@@ -32,7 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small Sr Yodas
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Yodas dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on merged datasets Common Voice 16 + Fleurs + [Juzne vesti (South news)](http://hdl.handle.net/11356/1679) + [LBM](https://huggingface.co/datasets/Sagicc/audio-lmb-ds) + (Yodas)[https://huggingface.co/datasets/espnet/yodas] dataset and
+
+Rupnik, Peter and Ljubešić, Nikola, 2022,\
+  ASR training dataset for Serbian JuzneVesti-SR v1.0, Slovenian language resource repository CLARIN.SI, ISSN 2820-4042,\
+  http://hdl.handle.net/11356/1679.
+  
 It achieves the following results on the evaluation set:
 - Loss: 0.3584
 - Wer Ortho: 0.2328
@@ -40,7 +48,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+Add new dataset Yodas as test and experiment to improve results.
 
 ## Intended uses & limitations
 
@@ -96,4 +104,4 @@ The following hyperparameters were used during training:
 - Transformers 4.39.3
 - Pytorch 2.0.1+cu117
 - Datasets 2.18.0
-- Tokenizers 0.15.1
+- Tokenizers 0.15.1