added bsize for open-asr eval

README.md

@@ -383,7 +383,7 @@ canary-180m-flash <br>
 ## Training Dataset:
 
 The canary-180m-flash model is trained on a total of 85K hrs of speech data. It consists of 31K hrs of public data, 20K hrs collected by [Suno](https://suno.ai/), and 34K hrs of in-house data. 
-The datasets below include conversations, videos from the web and audiobook recordings.
+The datasets below include conversations, videos from the web, and audiobook recordings.
 
 **Data Collection Method:**
 * Human <br>
@@ -476,7 +476,7 @@ In both ASR and AST experiments, predictions were generated using beam search wi
 
 The ASR performance is measured with word error rate (WER), and we process the groundtruth and predicted text with [whisper-normalizer](https://pypi.org/project/whisper-normalizer/).
 
-WER on [HuggingFace OpenASR leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard):
+WER on [HuggingFace OpenASR leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) evaluated with a batch size of 128:
 
 | **Version** | **Model**     | **RTFx**   | **AMI**   | **GigaSpeech**   | **LS Clean**   | **LS Other**   | **Earnings22**   | **SPGISpech**   | **Tedlium**   | **Voxpopuli**   |
 |:---------:|:-----------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|