Update README.md
Browse files
README.md
CHANGED
@@ -59,3 +59,17 @@ The model has been finetuned on Coommonvoice-v13 (FR) for 14 epochs on 4x2080 Ti
|
|
59 |
|
60 |
- The set of hyperparameters used for training are the same as those detailed in Annex B and Table 6 of [wav2vec2 paper](https://arxiv.org/pdf/2006.11477.pdf).
|
61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
- The set of hyperparameters used for training are the same as those detailed in Annex B and Table 6 of [wav2vec2 paper](https://arxiv.org/pdf/2006.11477.pdf).
|
61 |
|
62 |
+
## Usage (with HuggingSound)
|
63 |
+
|
64 |
+
The model can be used directly using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
|
65 |
+
|
66 |
+
```python
|
67 |
+
from huggingsound import SpeechRecognitionModel
|
68 |
+
|
69 |
+
model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-french")
|
70 |
+
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
|
71 |
+
|
72 |
+
transcriptions = model.transcribe(audio_paths)
|
73 |
+
```
|
74 |
+
|
75 |
+
## Usage
|