Instructions to use bond005/whisper-large-v2-ru-podlodka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bond005/whisper-large-v2-ru-podlodka with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bond005/whisper-large-v2-ru-podlodka")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("bond005/whisper-large-v2-ru-podlodka") model = AutoModelForSpeechSeq2Seq.from_pretrained("bond005/whisper-large-v2-ru-podlodka", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -48,4 +48,15 @@ model-index:
|
|
| 48 |
- name: WER (without punctuation)
|
| 49 |
type: wer
|
| 50 |
value: 9.0987
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
---
|
|
|
|
| 48 |
- name: WER (without punctuation)
|
| 49 |
type: wer
|
| 50 |
value: 9.0987
|
| 51 |
+
- task:
|
| 52 |
+
name: Speech Recognition
|
| 53 |
+
type: automatic-speech-recognition
|
| 54 |
+
dataset:
|
| 55 |
+
name: Russian Librispeech
|
| 56 |
+
type: bond005/rulibrispeech
|
| 57 |
+
args: ru
|
| 58 |
+
metrics:
|
| 59 |
+
- name: WER (without punctuation)
|
| 60 |
+
type: wer
|
| 61 |
+
value: 20.961
|
| 62 |
---
|