bofenghuang commited on
Commit
76de656
1 Parent(s): 494ea20
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -42,10 +42,10 @@ img {
42
 
43
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2), trained on the mozilla-foundation/common_voice_11_0 de dataset. When using the model make sure that your speech input is also sampled at 16Khz. **This model also predicts casing and punctuation.**
44
 
45
- Reported WERs on the [Common Voice 9.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) in the original [paper](https://cdn.openai.com/papers/whisper.pdf).
46
 
47
- | Model | WER |
48
- | --- | :---: |
49
  | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 13.0 |
50
  | [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 8.5 |
51
  | [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 6.4 |
 
42
 
43
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2), trained on the mozilla-foundation/common_voice_11_0 de dataset. When using the model make sure that your speech input is also sampled at 16Khz. **This model also predicts casing and punctuation.**
44
 
45
+ Reported WERs in the original [paper](https://cdn.openai.com/papers/whisper.pdf).
46
 
47
+ | Model | WER on the [Common Voice 9.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) |
48
+ | ------------------------ | :---: |
49
  | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 13.0 |
50
  | [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 8.5 |
51
  | [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 6.4 |