Update Model Card

README.md

@@ -119,7 +119,7 @@ The NeMo toolkit was used for finetuning this model for **16,296 steps** over `p
 The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
 
 ## Dataset
-This model was fine-tuned on the [bam-asr-all](https://huggingface.co/datasets/RobotsMali/bam-asr-all) dataset, which consists of 37 hours of transcribed Bambara speech data. The dataset is primarily derived from **Jeli-ASR dataset** (~87%).
+This model was fine-tuned on the [bam-asr-early](https://huggingface.co/datasets/RobotsMali/bam-asr-early) dataset, which consists of 37 hours of transcribed Bambara speech data. The dataset is primarily derived from **Jeli-ASR dataset** (~87%).
 
 ## Performance