Hugging Face's logo

efficient-speech
/
lite-whisper-large-v3-turbo

Automatic Speech Recognition
Transformers
Safetensors
lite-whisper
feature-extraction
audio
whisper
hf-asr-leaderboard
custom_code
Model card Files Community
3
eyoel-gebre commited on
Commit
6697ac2
·
verified ·
1 Parent(s): 56bee5a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -17
README.md CHANGED
@@ -22,25 +22,17 @@ Following is the average word error rate (WER) evaluated on the [ESB datasets](h
22
 
23
  | Model | Average WER (↓) | Encoder Size | Decoder Size |
24
  |-------|----------------|--------------|--------------|
25
- | [whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 22.01 | 7.63M | 29.55M |
26
- | [lite-whisper-tiny-acc](https://huggingface.co/efficient-speech/lite-whisper-tiny-acc) | 22.97 | 7.41M | 29.55M |
27
- | [lite-whisper-tiny](https://huggingface.co/efficient-speech/lite-whisper-tiny) | 23.95 | 7.00M | 29.55M |
28
- | [lite-whisper-tiny-fast](https://huggingface.co/efficient-speech/lite-whisper-tiny-fast) | 27.09 | 6.48M | 29.55M |
29
  |   |   |   |   |
30
- | [whisper-base](https://huggingface.co/openai/whisper-base) | 17.67 | 19.82M | 52.00M |
31
- | [lite-whisper-base-acc](https://huggingface.co/efficient-speech/lite-whisper-base-acc) | 19.07 | 18.64M | 52.00M |
32
- | [lite-whisper-base](https://huggingface.co/efficient-speech/lite-whisper-base) | 19.71 | 17.44M | 52.00M |
33
- | [lite-whisper-base-fast](https://huggingface.co/efficient-speech/lite-whisper-base-fast) | 23.05 | 16.07M | 52.00M |
34
  |   |   |   |   |
35
- | [whisper-small](https://huggingface.co/openai/whisper-small) | 15.89 | 87.00M | 153.58M |
36
- | [lite-whisper-small-acc](https://huggingface.co/efficient-speech/lite-whisper-small-acc) | 15.37 | 76.99M | 153.58M |
37
- | [lite-whisper-small](https://huggingface.co/efficient-speech/lite-whisper-small) | 14.96 | 70.16M | 153.58M |
38
- | [lite-whisper-small-fast](https://huggingface.co/efficient-speech/lite-whisper-small-fast) | 14.92 | 63.11M | 153.58M |
39
- |   |   |   |   |
40
- | [whisper-medium](https://huggingface.co/openai/whisper-medium) | 15.12 | 305.68M | 456.64M |
41
- | [lite-whisper-medium-acc](https://huggingface.co/efficient-speech/lite-whisper-medium-acc) | 13.46 | 269.93M | 456.64M |
42
- | [lite-whisper-medium](https://huggingface.co/efficient-speech/lite-whisper-medium) | 14.50 | 239.99M | 456.64M |
43
- | [lite-whisper-medium-fast](https://huggingface.co/efficient-speech/lite-whisper-medium-fast) | 14.52 | 215.31M | 456.64M |
44
 
45
 
46
  ## Citation
 
22
 
23
  | Model | Average WER (↓) | Encoder Size | Decoder Size |
24
  |-------|----------------|--------------|--------------|
25
+ | [whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 10.1 | 635M | 907M |
26
+ | [lite-whisper-large-v3-acc](https://huggingface.co/efficient-speech/lite-whisper-large-v3-acc) | 10.1 | 429M | 907M |
27
+ | [lite-whisper-large-v3](https://huggingface.co/efficient-speech/lite-whisper-large-v3) | 10.2 | 377M | 907M |
28
+ | [lite-whisper-large-v3-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-fast) | 11.3 | 308M | 907M |
29
  |   |   |   |   |
30
+ | [whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) | 10.1 | 635M | 172M |
31
+ | [lite-whisper-large-v3-turbo-acc](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-acc) | 10.2 | 421M | 172M |
32
+ | [lite-whisper-large-v3-turbo](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo) | 12.6 | 374M | 172M |
33
+ | [lite-whisper-large-v3-turbo-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-fast) | 20.1 | 313M | 172M |
34
  |   |   |   |   |
35
+ | [whisper-medium](https://huggingface.co/openai/whisper-medium) | 14.8 | 306M | 457M |
 
 
 
 
 
 
 
 
36
 
37
 
38
  ## Citation