Automatic Speech Recognition
audio
ericchin commited on
Commit
469373b
1 Parent(s): aa805c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -4
README.md CHANGED
@@ -125,13 +125,9 @@ This model architecture is used in [THIS REPO(Intel)](https://github.com/intel-s
125
  | Model Type | Parameters | 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 | n_vocab |
126
  |---------------------------|------------|-------------|---------------|--------------|---------------|------------|--------------|-------------|--------------|--------|---------|
127
  | whisper_tiny | 39 M | 1500 | 384 | 6 | 4 | 224 | 384 | 6 | 4 | 80 | 51864 |
128
- | whisper_tiny.en | 39 M | 1500 | 384 | 6 | 4 | 224 | 384 | 6 | 4 | 80 | 51864 |
129
  | whisper_base | 74 M | 1500 | 512 | 8 | 6 | 224 | 512 | 8 | 6 | 80 | 51864 |
130
- | whisper_base.en | 74 M | 1500 | 512 | 8 | 6 | 224 | 512 | 8 | 6 | 80 | 51864 |
131
  | **whisper_small** | 244 M | 1500 | 768 | 12 | 12 | 224 | 768 | 12 | 12 | 80 | 51864 |
132
- | whisper_small.en | 244 M | 1500 | 768 | 12 | 12 | 224 | 768 | 12 | 12 | 80 | 51864 |
133
  | whisper_medium | 769 M | 1500 | 1024 | 16 | 24 | 224 | 1024 | 16 | 16 | 80 | 51864 |
134
- | whisper_medium.en | 769 M | 1500 | 1024 | 16 | 24 | 224 | 1024 | 16 | 16 | 80 | 51864 |
135
  | whisper_large_v1 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |
136
  | whisper_large_v2 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |
137
  | whisper_large_v3 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |
 
125
  | Model Type | Parameters | 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 | n_vocab |
126
  |---------------------------|------------|-------------|---------------|--------------|---------------|------------|--------------|-------------|--------------|--------|---------|
127
  | whisper_tiny | 39 M | 1500 | 384 | 6 | 4 | 224 | 384 | 6 | 4 | 80 | 51864 |
 
128
  | whisper_base | 74 M | 1500 | 512 | 8 | 6 | 224 | 512 | 8 | 6 | 80 | 51864 |
 
129
  | **whisper_small** | 244 M | 1500 | 768 | 12 | 12 | 224 | 768 | 12 | 12 | 80 | 51864 |
 
130
  | whisper_medium | 769 M | 1500 | 1024 | 16 | 24 | 224 | 1024 | 16 | 16 | 80 | 51864 |
 
131
  | whisper_large_v1 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |
132
  | whisper_large_v2 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |
133
  | whisper_large_v3 | 1550 M | 1500 | 1280 | 20 | 32 | 224 | 1280 | 20 | 20 | 80 | 51864 |