Update README.md
Browse files(bam-asr-all) en (bam-asr-early )
README.md
CHANGED
@@ -127,7 +127,7 @@ The performance of Automatic Speech Recognition models is measured using Word Er
|
|
127 |
|
128 |
The following table summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of **Word Error Rate (WER%)**.
|
129 |
|
130 |
-
|**Decoder (Version)**|**Tokenizer**|**Vocabulary Size**|**bam-asr-
|
131 |
|---------|-----------------------|-----------------|---------|
|
132 |
| CTC (V6) | BPE | 1024 | 40.6 |
|
133 |
| TDT (V6) | BPE | 1024 | 66.7 |
|
|
|
127 |
|
128 |
The following table summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of **Word Error Rate (WER%)**.
|
129 |
|
130 |
+
|**Decoder (Version)**|**Tokenizer**|**Vocabulary Size**|**bam-asr-early (test set)**|
|
131 |
|---------|-----------------------|-----------------|---------|
|
132 |
| CTC (V6) | BPE | 1024 | 40.6 |
|
133 |
| TDT (V6) | BPE | 1024 | 66.7 |
|