Hugging Face's logo

okestro-ai-lab
/
FastSLM-ASR

Audio-Text-to-Text
Transformers
Safetensors
English
Korean
fastslm
feature-extraction
audio
text-generation
custom_code
Eval Results
Model card Files
xet
 Community
1
speechisalluneed commited on
Commit
f04fefe
·
verified ·
1 Parent(s): ee348f8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -28,7 +28,7 @@ model-index:
28
  metrics:
29
  - name: Test WER
30
  type: wer
31
- value: 9.89
32
  - task:
33
  name: Automatic Speech Recognition
34
  type: automatic-speech-recognition
@@ -41,7 +41,7 @@ model-index:
41
  metrics:
42
  - name: Test WER
43
  type: wer
44
- value: 9.84
45
  - task:
46
  name: Automatic Speech Recognition
47
  type: automatic-speech-recognition
@@ -54,7 +54,7 @@ model-index:
54
  metrics:
55
  - name: Test WER
56
  type: wer
57
- value: 9.99
58
  - task:
59
  name: Automatic Speech Recognition
60
  type: automatic-speech-recognition
@@ -68,7 +68,7 @@ model-index:
68
  metrics:
69
  - name: Test WER
70
  type: wer
71
- value: 1.92
72
  - task:
73
  name: Automatic Speech Recognition
74
  type: automatic-speech-recognition
@@ -82,7 +82,7 @@ model-index:
82
  metrics:
83
  - name: Test WER
84
  type: wer
85
- value: 4.52
86
  - task:
87
  name: Automatic Speech Recognition
88
  type: automatic-speech-recognition
@@ -96,7 +96,7 @@ model-index:
96
  metrics:
97
  - name: Test WER
98
  type: wer
99
- value: 6.65
100
  - task:
101
  type: Automatic Speech Recognition
102
  name: automatic-speech-recognition
@@ -110,7 +110,7 @@ model-index:
110
  metrics:
111
  - name: Test WER
112
  type: wer
113
- value: 3.58
114
  - task:
115
  type: Automatic Speech Recognition
116
  name: automatic-speech-recognition
@@ -124,7 +124,7 @@ model-index:
124
  metrics:
125
  - name: Test WER
126
  type: wer
127
- value: 2.23
128
  ---
129
 
130
  # 🚀 FastSLM: Hierarchical Frame Q-Former for Effective Speech Modality Adaptation
 
28
  metrics:
29
  - name: Test WER
30
  type: wer
31
+ value: 9.55
32
  - task:
33
  name: Automatic Speech Recognition
34
  type: automatic-speech-recognition
 
41
  metrics:
42
  - name: Test WER
43
  type: wer
44
+ value: 10.27
45
  - task:
46
  name: Automatic Speech Recognition
47
  type: automatic-speech-recognition
 
54
  metrics:
55
  - name: Test WER
56
  type: wer
57
+ value: 9.89
58
  - task:
59
  name: Automatic Speech Recognition
60
  type: automatic-speech-recognition
 
68
  metrics:
69
  - name: Test WER
70
  type: wer
71
+ value: 1.93
72
  - task:
73
  name: Automatic Speech Recognition
74
  type: automatic-speech-recognition
 
82
  metrics:
83
  - name: Test WER
84
  type: wer
85
+ value: 4.43
86
  - task:
87
  name: Automatic Speech Recognition
88
  type: automatic-speech-recognition
 
96
  metrics:
97
  - name: Test WER
98
  type: wer
99
+ value: 6.33
100
  - task:
101
  type: Automatic Speech Recognition
102
  name: automatic-speech-recognition
 
110
  metrics:
111
  - name: Test WER
112
  type: wer
113
+ value: 3.41
114
  - task:
115
  type: Automatic Speech Recognition
116
  name: automatic-speech-recognition
 
124
  metrics:
125
  - name: Test WER
126
  type: wer
127
+ value: 2.27
128
  ---
129
 
130
  # 🚀 FastSLM: Hierarchical Frame Q-Former for Effective Speech Modality Adaptation