Update metrics metadata
Browse files
README.md
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
---
|
2 |
-
language:
|
|
|
3 |
library_name: nemo
|
4 |
datasets:
|
5 |
- librispeech_asr
|
@@ -14,7 +15,7 @@ datasets:
|
|
14 |
- Europarl-ASR (EN)
|
15 |
- Multilingual LibriSpeech (2000 hours)
|
16 |
- mozilla-foundation/common_voice_7_0
|
17 |
-
thumbnail:
|
18 |
tags:
|
19 |
- automatic-speech-recognition
|
20 |
- speech
|
@@ -32,96 +33,114 @@ widget:
|
|
32 |
- example_title: Librispeech sample 2
|
33 |
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
|
34 |
model-index:
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
125 |
---
|
126 |
## Model Overview
|
127 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
library_name: nemo
|
5 |
datasets:
|
6 |
- librispeech_asr
|
|
|
15 |
- Europarl-ASR (EN)
|
16 |
- Multilingual LibriSpeech (2000 hours)
|
17 |
- mozilla-foundation/common_voice_7_0
|
18 |
+
thumbnail: null
|
19 |
tags:
|
20 |
- automatic-speech-recognition
|
21 |
- speech
|
|
|
33 |
- example_title: Librispeech sample 2
|
34 |
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
|
35 |
model-index:
|
36 |
+
- name: stt_en_conformer_ctc_large
|
37 |
+
results:
|
38 |
+
- task:
|
39 |
+
name: Automatic Speech Recognition
|
40 |
+
type: automatic-speech-recognition
|
41 |
+
dataset:
|
42 |
+
name: LibriSpeech (clean)
|
43 |
+
type: librispeech_asr
|
44 |
+
config: clean
|
45 |
+
split: test
|
46 |
+
args:
|
47 |
+
language: en
|
48 |
+
metrics:
|
49 |
+
- name: Test WER
|
50 |
+
type: wer
|
51 |
+
value: 2.2
|
52 |
+
- task:
|
53 |
+
type: Automatic Speech Recognition
|
54 |
+
name: automatic-speech-recognition
|
55 |
+
dataset:
|
56 |
+
name: LibriSpeech (other)
|
57 |
+
type: librispeech_asr
|
58 |
+
config: other
|
59 |
+
split: test
|
60 |
+
args:
|
61 |
+
language: en
|
62 |
+
metrics:
|
63 |
+
- name: Test WER
|
64 |
+
type: wer
|
65 |
+
value: 4.3
|
66 |
+
- task:
|
67 |
+
type: Automatic Speech Recognition
|
68 |
+
name: automatic-speech-recognition
|
69 |
+
dataset:
|
70 |
+
name: Multilingual LibriSpeech
|
71 |
+
type: facebook/multilingual_librispeech
|
72 |
+
config: english
|
73 |
+
split: test
|
74 |
+
args:
|
75 |
+
language: en
|
76 |
+
metrics:
|
77 |
+
- name: Test WER
|
78 |
+
type: wer
|
79 |
+
value: 7.2
|
80 |
+
- task:
|
81 |
+
type: Automatic Speech Recognition
|
82 |
+
name: automatic-speech-recognition
|
83 |
+
dataset:
|
84 |
+
name: Mozilla Common Voice 7.0
|
85 |
+
type: mozilla-foundation/common_voice_7_0
|
86 |
+
config: en
|
87 |
+
split: test
|
88 |
+
args:
|
89 |
+
language: en
|
90 |
+
metrics:
|
91 |
+
- name: Test WER
|
92 |
+
type: wer
|
93 |
+
value: 8.0
|
94 |
+
- task:
|
95 |
+
type: Automatic Speech Recognition
|
96 |
+
name: automatic-speech-recognition
|
97 |
+
dataset:
|
98 |
+
name: Mozilla Common Voice 8.0
|
99 |
+
type: mozilla-foundation/common_voice_8_0
|
100 |
+
config: en
|
101 |
+
split: test
|
102 |
+
args:
|
103 |
+
language: en
|
104 |
+
metrics:
|
105 |
+
- name: Test WER
|
106 |
+
type: wer
|
107 |
+
value: 9.48
|
108 |
+
- task:
|
109 |
+
type: Automatic Speech Recognition
|
110 |
+
name: automatic-speech-recognition
|
111 |
+
dataset:
|
112 |
+
name: Wall Street Journal 92
|
113 |
+
type: wsj_0
|
114 |
+
args:
|
115 |
+
language: en
|
116 |
+
metrics:
|
117 |
+
- name: Test WER
|
118 |
+
type: wer
|
119 |
+
value: 2.0
|
120 |
+
- task:
|
121 |
+
type: Automatic Speech Recognition
|
122 |
+
name: automatic-speech-recognition
|
123 |
+
dataset:
|
124 |
+
name: Wall Street Journal 93
|
125 |
+
type: wsj_1
|
126 |
+
args:
|
127 |
+
language: en
|
128 |
+
metrics:
|
129 |
+
- name: Test WER
|
130 |
+
type: wer
|
131 |
+
value: 2.9
|
132 |
+
- task:
|
133 |
+
type: Automatic Speech Recognition
|
134 |
+
name: automatic-speech-recognition
|
135 |
+
dataset:
|
136 |
+
name: National Singapore Corpus
|
137 |
+
type: nsc_part_1
|
138 |
+
args:
|
139 |
+
language: en
|
140 |
+
metrics:
|
141 |
+
- name: Test WER
|
142 |
+
type: wer
|
143 |
+
value: 7.0
|
144 |
---
|
145 |
## Model Overview
|
146 |
|