Automatic Speech Recognition
audio
ericchin commited on
Commit
1392cce
·
verified ·
1 Parent(s): bd63f8b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -124,14 +124,14 @@ This model architecture is used in [THIS REPO(Intel)](https://github.com/intel-s
124
 
125
  | Model Type | n_vocab | n_audio_ctx | n_audio_state | n_audio_head | n_audio_layer | n_text_ctx | n_text_state | n_text_head | n_text_layer | n_mels | Parameters |
126
  |---------------------------|---------|-------------|---------------|--------------|---------------|------------|--------------|-------------|--------------|--------|------------|
127
- | whisper_tiny | 51864 | 1500 | 512 | 6 | 4 | 128 | 512 | 6 | 4 | 80 | 39 M |
128
- | whisper_tiny.en | 51864 | 1500 | 512 | 6 | 4 | 128 | 512 | 6 | 4 | 80 | 39 M |
129
  | whisper_base | 51864 | 1500 | 512 | 8 | 6 | 128 | 512 | 8 | 6 | 80 | 74 M |
130
  | whisper_base.en | 51864 | 1500 | 512 | 8 | 6 | 128 | 512 | 8 | 6 | 80 | 74 M |
131
- | whisper_small | 51864 | 1500 | 512 | 12 | 12 | 128 | 512 | 12 | 12 | 80 | 244 M |
132
- | whisper_small.en | 51864 | 1500 | 512 | 12 | 12 | 128 | 512 | 12 | 12 | 80 | 244 M |
133
- | whisper_medium | 51864 | 1500 | 512 | 16 | 24 | 128 | 512 | 16 | 16 | 80 | 769 M |
134
- | whisper_medium.en | 51864 | 1500 | 512 | 16 | 24 | 128 | 512 | 16 | 16 | 80 | 769 M |
135
- | whisper_large_v1 | 51864 | 1500 | 512 | 20 | 32 | 128 | 512 | 20 | 20 | 80 | 1550 M |
136
- | whisper_large_v2 | 51864 | 1500 | 512 | 20 | 32 | 128 | 512 | 20 | 20 | 80 | 1550 M |
137
- | whisper_large_v3 | 51864 | 1500 | 512 | 20 | 32 | 128 | 512 | 20 | 20 | 80 | 1550 M |
 
124
 
125
  | Model Type | n_vocab | n_audio_ctx | n_audio_state | n_audio_head | n_audio_layer | n_text_ctx | n_text_state | n_text_head | n_text_layer | n_mels | Parameters |
126
  |---------------------------|---------|-------------|---------------|--------------|---------------|------------|--------------|-------------|--------------|--------|------------|
127
+ | whisper_tiny | 51864 | 1500 | 384 | 6 | 4 | 128 | 384 | 6 | 4 | 80 | 39 M |
128
+ | whisper_tiny.en | 51864 | 1500 | 384 | 6 | 4 | 128 | 384 | 6 | 4 | 80 | 39 M |
129
  | whisper_base | 51864 | 1500 | 512 | 8 | 6 | 128 | 512 | 8 | 6 | 80 | 74 M |
130
  | whisper_base.en | 51864 | 1500 | 512 | 8 | 6 | 128 | 512 | 8 | 6 | 80 | 74 M |
131
+ | whisper_small | 51864 | 1500 | 768 | 12 | 12 | 128 | 768 | 12 | 12 | 80 | 244 M |
132
+ | whisper_small.en | 51864 | 1500 | 768 | 12 | 12 | 128 | 768 | 12 | 12 | 80 | 244 M |
133
+ | whisper_medium | 51864 | 1500 | 1024 | 16 | 24 | 128 | 1024 | 16 | 16 | 80 | 769 M |
134
+ | whisper_medium.en | 51864 | 1500 | 1024 | 16 | 24 | 128 | 1024 | 16 | 16 | 80 | 769 M |
135
+ | whisper_large_v1 | 51864 | 1500 | 1280 | 20 | 32 | 128 | 1280 | 20 | 20 | 80 | 1550 M |
136
+ | whisper_large_v2 | 51864 | 1500 | 1280 | 20 | 32 | 128 | 1280 | 20 | 20 | 80 | 1550 M |
137
+ | whisper_large_v3 | 51864 | 1500 | 1280 | 20 | 32 | 128 | 1280 | 20 | 20 | 80 | 1550 M |