|
--- |
|
language: |
|
- en |
|
tags: |
|
- openvino |
|
--- |
|
|
|
# anton-l/wav2vec2-base-superb-sd |
|
|
|
This is the [anton-l/wav2vec2-base-superb-sd](https://huggingface.co/anton-l/wav2vec2-base-superb-sd) model converted to [OpenVINO](https://openvino.ai), for accelerated inference. |
|
|
|
An example of how to do inference on this model: |
|
```python |
|
from optimum.intel import OVModelForAudioFrameClassification |
|
from transformers import AutoFeatureExtractor, pipeline |
|
|
|
# model_id should be set to either a local directory or a model available on the HuggingFace hub. |
|
model_id = "helenai/anton-l-wav2vec2-base-superb-sd-ov" |
|
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id, trust_remote_code=True) |
|
model = OVModelForAudioFrameClassification.from_pretrained(model_id) |
|
pipe = pipeline("None", model=model, feature_extractor=feature_extractor) |
|
result = pipe("hello world") |
|
print(result) |
|
``` |
|
|
|
|
