Upload README.md

README.md

@@ -61,11 +61,21 @@ The model should be loaded with `trust_remote_code=True`. The official inference
 
 The following results are from the `open-audio-opd` evaluation. Lower CER/WER is better.
 
-| Model | AMI WER | Earnings22 WER | GigaSpeech WER | LS Clean WER | LS Other WER | SPGISpeech WER | VoxPopuli WER | English Avg WER | AISHELL-1 CER | Wenet-meeting CER | Wenet-net CER | Chinese Avg CER |
-| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
-| Ark-ASR | 11.67% | 10.11% | 8.93% | 1.93% | 4.00% | 2.89% | 6.96% | 6.64% | 2.02% | 5.92% | 4.96% | 4.30% |
-| Qwen3-ASR-1.7B | 10.56% | 10.25% | 8.74% | 1.63% | 3.40% | 2.84% | 6.35% | 6.25% | 1.50% | 4.69% | 4.55% | 3.58% |
-| Qwen3-ASR-0.6B | 11.66% | 11.06% | 9.14% | 2.13% | 4.45% | 3.03% | 7.07% | 6.93% | 2.07% | 5.57% | 5.45% | 4.36% |
+### English WER
+
+| Model | AMI | Earnings22 | GigaSpeech | LS Clean | LS Other | SPGISpeech | VoxPopuli | Avg |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| Ark-ASR | 11.67% | 10.11% | 8.93% | 1.93% | 4.00% | 2.89% | 6.96% | 6.64% |
+| Qwen3-ASR-1.7B | 10.56% | 10.25% | 8.74% | 1.63% | 3.40% | 2.84% | 6.35% | 6.25% |
+| Qwen3-ASR-0.6B | 11.66% | 11.06% | 9.14% | 2.13% | 4.45% | 3.03% | 7.07% | 6.93% |
+
+### Chinese CER
+
+| Model | AISHELL-1 | Wenet-meeting | Wenet-net | Avg |
+| --- | ---: | ---: | ---: | ---: |
+| Ark-ASR | 2.02% | 5.92% | 4.96% | 4.30% |
+| Qwen3-ASR-1.7B | 1.50% | 4.69% | 4.55% | 3.58% |
+| Qwen3-ASR-0.6B | 2.07% | 5.57% | 5.45% | 4.36% |
 
 `Ark-ASR` is the 0.6B ASR checkpoint trained with teacher-data adaptation and on-policy distillation from `open-audio-opd`.