fix

Author: yanghaha0908

examples/contextual_asr/README.md

@@ -26,6 +26,7 @@ They categorize the 5,000 most frequent words in the Librispeech training corpus
 words, with the remainder classified as rare words. The biasing list generated for the test set consists of two segments: rare words in the transcriptions, and distractors sampled from the 209.2K rare words vocabulary. Biasing lists of varying lengths are generated by incorporating N = {100, 500, 1000, 2000} distractors into the lists.
 
 
+The viterbi decode results of our CTC Fine-tuned WavLM-Large: [test-clean](https://drive.google.com/file/d/1kMzPx8oRK3aOsxNaMGski3zH8z5Otvek/view?usp=drive_link), [test-other](https://drive.google.com/file/d/12KHaatVg5O0MIBTcf8e_rNjV_i9WLBFR/view?usp=drive_link) (``ctc_file`` in contextual_asr_config.py)
 
 ## Decoding with checkpoints
 LLM-based ASR Inference script.