Commit
•
c3612a9
1
Parent(s):
d1c1288
Update README.md (#3)
Browse files- Update README.md (6e7b279b06963e7372ed3f80ad45d34773bd5922)
Co-authored-by: Nikolay <nkarpov@users.noreply.huggingface.co>
README.md
CHANGED
@@ -34,7 +34,7 @@ model-index:
|
|
34 |
metrics:
|
35 |
- name: Test WER
|
36 |
type: wer
|
37 |
-
value: 5.
|
38 |
- task:
|
39 |
name: Automatic Speech Recognition
|
40 |
type: automatic-speech-recognition
|
@@ -48,7 +48,7 @@ model-index:
|
|
48 |
metrics:
|
49 |
- name: Test WER P&C
|
50 |
type: wer
|
51 |
-
value:
|
52 |
---
|
53 |
|
54 |
# NVIDIA FastConformer-Hybrid Large (ua)
|
@@ -148,13 +148,13 @@ The following tables summarizes the performance of the available models in this
|
|
148 |
a) On data without Punctuation and Capitalization with Transducer decoder
|
149 |
| **Version** | **Tokenizer** | **Vocabulary Size** | **MCV12 TEST** |
|
150 |
|:-----------:|:---------------------:|:-------------------:|:-------------:|
|
151 |
-
| 1.0.
|
152 |
|
153 |
|
154 |
b) On data with Punctuation and Capitalization with Transducer decoder
|
155 |
| **Version** | **Tokenizer** | **Vocabulary Size** | **MCV12 TEST** |
|
156 |
|:-----------:|:---------------------:|:-------------------:|:-------------:|
|
157 |
-
| 1.0.
|
158 |
|
159 |
|
160 |
## Limitations
|
|
|
34 |
metrics:
|
35 |
- name: Test WER
|
36 |
type: wer
|
37 |
+
value: 5.66
|
38 |
- task:
|
39 |
name: Automatic Speech Recognition
|
40 |
type: automatic-speech-recognition
|
|
|
48 |
metrics:
|
49 |
- name: Test WER P&C
|
50 |
type: wer
|
51 |
+
value: 8.06
|
52 |
---
|
53 |
|
54 |
# NVIDIA FastConformer-Hybrid Large (ua)
|
|
|
148 |
a) On data without Punctuation and Capitalization with Transducer decoder
|
149 |
| **Version** | **Tokenizer** | **Vocabulary Size** | **MCV12 TEST** |
|
150 |
|:-----------:|:---------------------:|:-------------------:|:-------------:|
|
151 |
+
| 1.0.2 | SentencePiece Unigram | 512 | 5.66 |
|
152 |
|
153 |
|
154 |
b) On data with Punctuation and Capitalization with Transducer decoder
|
155 |
| **Version** | **Tokenizer** | **Vocabulary Size** | **MCV12 TEST** |
|
156 |
|:-----------:|:---------------------:|:-------------------:|:-------------:|
|
157 |
+
| 1.0.2 | SentencePiece Unigram | 512 | 8.06 |
|
158 |
|
159 |
|
160 |
## Limitations
|