Hugging Face's logo

skit-ai
/
speechllm-2B

Feature Extraction
Transformers
Safetensors
English
custom_model
multi-modal
speech-language
custom_code
Eval Results
Model card Files
xet
Community
shangeth commited on
Commit
8036924
·
verified ·
1 Parent(s): fd28fab

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -3
README.md CHANGED
@@ -8,6 +8,7 @@ datasets:
8
  - openslr/librispeech_asr
9
  metrics:
10
  - wer
 
11
  model-index:
12
  - name: SpeechLLM
13
  results:
@@ -23,7 +24,7 @@ model-index:
23
  language: en
24
  metrics:
25
  - type: wer
26
- value: 12.3
27
  name: Test WER
28
  - task:
29
  type: automatic-speech-recognition
@@ -37,7 +38,7 @@ model-index:
37
  language: en
38
  metrics:
39
  - type: wer
40
- value: 18.9
41
  name: Test WER
42
  - task:
43
  type: automatic-speech-recognition
@@ -50,8 +51,34 @@ model-index:
50
  language: en
51
  metrics:
52
  - type: wer
53
- value: 25.01
54
  name: Test WER
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ---
56
 
57
  # SpeechLLM
 
8
  - openslr/librispeech_asr
9
  metrics:
10
  - wer
11
+ - accuracy
12
  model-index:
13
  - name: SpeechLLM
14
  results:
 
24
  language: en
25
  metrics:
26
  - type: wer
27
+ value: 7.3
28
  name: Test WER
29
  - task:
30
  type: automatic-speech-recognition
 
38
  language: en
39
  metrics:
40
  - type: wer
41
+ value: 10.47
42
  name: Test WER
43
  - task:
44
  type: automatic-speech-recognition
 
51
  language: en
52
  metrics:
53
  - type: wer
54
+ value: 24.47
55
  name: Test WER
56
+ - task:
57
+ type: audio-classification
58
+ name: Audio Classification
59
+ dataset:
60
+ name: Common Voice 16.1
61
+ type: common_voice_16_1
62
+ split: test
63
+ args:
64
+ language: en
65
+ metrics:
66
+ - type: accuracy
67
+ value: 60.61
68
+ name: Test Age Accuracy
69
+ - task:
70
+ type: audio-classification
71
+ name: Audio Classification
72
+ dataset:
73
+ name: Common Voice 16.1
74
+ type: common_voice_16_1
75
+ split: test
76
+ args:
77
+ language: en
78
+ metrics:
79
+ - type: accuracy
80
+ value: 61.56
81
+ name: Test Accent Accuracy
82
  ---
83
 
84
  # SpeechLLM