Commit
·
a43d5d7
1
Parent(s):
09b7359
Adding SSL finetuned model as new version
Browse files
README.md
CHANGED
|
@@ -63,7 +63,7 @@ model-index:
|
|
| 63 |
metrics:
|
| 64 |
- name: Test WER
|
| 65 |
type: wer
|
| 66 |
-
value:
|
| 67 |
- task:
|
| 68 |
type: Automatic Speech Recognition
|
| 69 |
name: automatic-speech-recognition
|
|
@@ -77,7 +77,7 @@ model-index:
|
|
| 77 |
metrics:
|
| 78 |
- name: Test WER
|
| 79 |
type: wer
|
| 80 |
-
value: 4.
|
| 81 |
- task:
|
| 82 |
type: Automatic Speech Recognition
|
| 83 |
name: automatic-speech-recognition
|
|
@@ -91,7 +91,7 @@ model-index:
|
|
| 91 |
metrics:
|
| 92 |
- name: Test WER
|
| 93 |
type: wer
|
| 94 |
-
value: 5.
|
| 95 |
- task:
|
| 96 |
type: Automatic Speech Recognition
|
| 97 |
name: automatic-speech-recognition
|
|
@@ -103,7 +103,7 @@ model-index:
|
|
| 103 |
metrics:
|
| 104 |
- name: Test WER
|
| 105 |
type: wer
|
| 106 |
-
value: 1.
|
| 107 |
- task:
|
| 108 |
type: Automatic Speech Recognition
|
| 109 |
name: automatic-speech-recognition
|
|
@@ -115,7 +115,7 @@ model-index:
|
|
| 115 |
metrics:
|
| 116 |
- name: Test WER
|
| 117 |
type: wer
|
| 118 |
-
value: 2.
|
| 119 |
- task:
|
| 120 |
name: Automatic Speech Recognition
|
| 121 |
type: automatic-speech-recognition
|
|
@@ -128,7 +128,7 @@ model-index:
|
|
| 128 |
metrics:
|
| 129 |
- name: Test WER
|
| 130 |
type: wer
|
| 131 |
-
value:
|
| 132 |
|
| 133 |
|
| 134 |
---
|
|
@@ -229,6 +229,7 @@ The following tables summarizes the performance of the available models in this
|
|
| 229 |
|**Version**|**Tokenizer**|**Vocabulary Size**|**LS test-other**|**LS test-clean**|**WSJ Eval92**|**WSJ Dev93**|**NSC Part 1**|**MLS Test**|**MCV Test 7.0**| Train Dataset |
|
| 230 |
|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-----|-------|------|------|
|
| 231 |
| 1.20.0 | SentencePiece Unigram | 1024 | 3.04 | 1.59 | 1.27 | 2.13 | 5.84 | 4.88 | 5.11 | NeMo ASRSET 3.0 |
|
|
|
|
| 232 |
|
| 233 |
|
| 234 |
## Limitations
|
|
|
|
| 63 |
metrics:
|
| 64 |
- name: Test WER
|
| 65 |
type: wer
|
| 66 |
+
value: 2.71
|
| 67 |
- task:
|
| 68 |
type: Automatic Speech Recognition
|
| 69 |
name: automatic-speech-recognition
|
|
|
|
| 77 |
metrics:
|
| 78 |
- name: Test WER
|
| 79 |
type: wer
|
| 80 |
+
value: 4.58
|
| 81 |
- task:
|
| 82 |
type: Automatic Speech Recognition
|
| 83 |
name: automatic-speech-recognition
|
|
|
|
| 91 |
metrics:
|
| 92 |
- name: Test WER
|
| 93 |
type: wer
|
| 94 |
+
value: 5.48
|
| 95 |
- task:
|
| 96 |
type: Automatic Speech Recognition
|
| 97 |
name: automatic-speech-recognition
|
|
|
|
| 103 |
metrics:
|
| 104 |
- name: Test WER
|
| 105 |
type: wer
|
| 106 |
+
value: 1.09
|
| 107 |
- task:
|
| 108 |
type: Automatic Speech Recognition
|
| 109 |
name: automatic-speech-recognition
|
|
|
|
| 115 |
metrics:
|
| 116 |
- name: Test WER
|
| 117 |
type: wer
|
| 118 |
+
value: 2.00
|
| 119 |
- task:
|
| 120 |
name: Automatic Speech Recognition
|
| 121 |
type: automatic-speech-recognition
|
|
|
|
| 128 |
metrics:
|
| 129 |
- name: Test WER
|
| 130 |
type: wer
|
| 131 |
+
value: 4.48
|
| 132 |
|
| 133 |
|
| 134 |
---
|
|
|
|
| 229 |
|**Version**|**Tokenizer**|**Vocabulary Size**|**LS test-other**|**LS test-clean**|**WSJ Eval92**|**WSJ Dev93**|**NSC Part 1**|**MLS Test**|**MCV Test 7.0**| Train Dataset |
|
| 230 |
|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-----|-------|------|------|
|
| 231 |
| 1.20.0 | SentencePiece Unigram | 1024 | 3.04 | 1.59 | 1.27 | 2.13 | 5.84 | 4.88 | 5.11 | NeMo ASRSET 3.0 |
|
| 232 |
+
| 1.20.1 | SentencePiece Unigram | 1024 | 2.71 | 1.50 | 1.09 | 2.00 | 4.48 | 4.32 | 5.48 | NeMo ASRSET 3.0 |
|
| 233 |
|
| 234 |
|
| 235 |
## Limitations
|