Update README.md

README.md

@@ -9,4 +9,46 @@ tags:
 ---
 
 # Fine-tuned Japanese Wav2Vec2 model for speech recognition using XLSR-53 large
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Japanese using [Common Voice](https://commonvoice.mozilla.org/ja/datasets), [JVS](https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_corpus) and [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut).
+When using this model, make sure that your speech input is sampled at 16kHz.
 
+## Usage
+The model can be used directly (without a language model) as follows.
+
+```python
+import torch
+import librosa
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+LANG_ID = "ja"
+MODEL_ID = "Ivydata/wav2vec2-large-xlsr-53-japanese"
+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)
+
+for i, predicted_sentence in enumerate(predicted_sentences):
+    print("-" * 100)
+    print("Reference: ", test_dataset[i]["sentence"])
+    print("Prediction:", predicted_sentence)
+```