Update README.md

README.md

@@ -59,10 +59,55 @@ model-index:
 Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on French using the [Common Voice 8](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0).
 When using this model, make sure that your speech input is sampled at 16kHz.
 
-This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
+This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool, and thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
 
-The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
+## Usage
 
+Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
+
+```python
+from huggingsound import SpeechRecognitionModel
+
+model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-xls-r-1b-french")
+audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
+
+transcriptions = model.transcribe(audio_paths)
+```
+
+Writing your own inference script:
+
+```python
+import torch
+import librosa
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+LANG_ID = "fr"
+MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-french"
+SAMPLES = 10
+
+test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
+
+processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
+model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    batch["sentence"] = batch["sentence"].upper()
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+with torch.no_grad():
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+predicted_sentences = processor.batch_decode(predicted_ids)
+```
 
 ## Evaluation Commands