Commit
•
494ea20
1
Parent(s):
306c7f2
up
Browse files
README.md
CHANGED
|
@@ -42,6 +42,15 @@ 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 |
## Usage
|
| 46 |
|
| 47 |
Inference with 🤗 Pipeline
|
|
|
|
| 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 |
|
| 52 |
+
|
| 53 |
+
|
| 54 |
## Usage
|
| 55 |
|
| 56 |
Inference with 🤗 Pipeline
|