Point dataset reference to renamed billingsmoore/nict-tib1 repo

README.md

@@ -12,7 +12,7 @@ tags:
 - 8bit
 base_model: openai/whisper-tiny
 datasets:
-- billingsmoore/tibetan-asr
+- billingsmoore/nict-tib1
 metrics:
 - cer
 - wer
@@ -23,7 +23,7 @@ model-index:
       type: automatic-speech-recognition
       name: Automatic Speech Recognition
     dataset:
-      type: billingsmoore/tibetan-asr
+      type: billingsmoore/nict-tib1
       name: NICT-Tib1 (Lhasa Tibetan)
       split: test
     metrics:
@@ -53,7 +53,7 @@ Base model weights are loaded in 8-bit precision (symmetric rounding, double qua
 
 ## Training data
 
-Fine-tuned on [NICT-Tib1](https://huggingface.co/datasets/billingsmoore/tibetan-asr), a corpus of transcribed Lhasa Tibetan speech from 20 speakers (Soky, Gong & Li, 2022). The data was split by speaker (85/15, not by utterance) so that no speaker appears in both splits: 15,099 training utterances from 17 speakers, 1,547 test utterances from the remaining 3 speakers.
+Fine-tuned on [NICT-Tib1](https://huggingface.co/datasets/billingsmoore/nict-tib1), a corpus of transcribed Lhasa Tibetan speech from 20 speakers (Soky, Gong & Li, 2022). The data was split by speaker (85/15, not by utterance) so that no speaker appears in both splits: 15,099 training utterances from 17 speakers, 1,547 test utterances from the remaining 3 speakers.
 
 ## Training procedure