Update README.md

README.md

@@ -2,7 +2,9 @@
 language: vi
 datasets:
 - common_voice
-- https://data.mendeley.com/datasets/k9sxg2twv4/4
+- TODO: https://data.mendeley.com/datasets/k9sxg2twv4/4
+metrics:
+- wer
 tags:
 - audio
 - automatic-speech-recognition
@@ -17,10 +19,109 @@ model-index:
       type: automatic-speech-recognition
     dataset:
       name: Common Voice vi
-      type: Common Voice
-      args: vi  
+      type: common_voice
+      args: vi
     metrics:
        - name: Test WER
          type: wer
          value: 99.99
----
+---
+
+# Wav2Vec2-Large-XLSR-53-{language} Vietnamese
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Vietnamese using the [Common Voice](https://huggingface.co/datasets/common_voice), and [FOSD](https://data.mendeley.com/datasets/k9sxg2twv4/4).
+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 torchaudio
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+test_dataset = load_dataset("common_voice", "vi", split="test[:2%]") 
+
+processor = Wav2Vec2Processor.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
+model = Wav2Vec2ForCTC.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def speech_file_to_array_fn(batch):
+	speech_array, sampling_rate = torchaudio.load(batch["path"])
+	batch["speech"] = resampler(speech_array).squeeze().numpy()
+	return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["speech"][:2], 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)
+
+print("Prediction:", processor.batch_decode(predicted_ids))
+print("Reference:", test_dataset["sentence"][:2])
+```
+
+
+## Evaluation
+
+The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
+
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import re
+
+test_dataset = load_dataset("common_voice", "vi", split="test")
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
+model = Wav2Vec2ForCTC.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
+model.to("cuda")
+
+chars_to_ignore_regex = '[\\\+\@\ǀ\,\?\.\!\-\;\:\"\“\%\‘\”\�0123456789]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def speech_file_to_array_fn(batch):
+	batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+	speech_array, sampling_rate = torchaudio.load(batch["path"])
+	batch["speech"] = resampler(speech_array).squeeze().numpy()
+	return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def evaluate(batch):
+	inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+	with torch.no_grad():
+		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+
+	pred_ids = torch.argmax(logits, dim=-1)
+	batch["pred_strings"] = processor.batch_decode(pred_ids)
+	return batch
+
+result = test_dataset.map(evaluate, batched=True, batch_size=8)
+
+print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+```
+
+**Test Result**: XX.XX %  # TODO: write output of print here. IMPORTANT: Please remember to also replace {wer_result_on_test} at the top of with this value here. tags.
+
+
+## Training
+
+The Common Voice `train`, `validation`, and FOSD datasets were used for training as well.
+
+The script used for training can be found [here](https://colab.research.google.com/drive/11pP4uVJj4SYZTzGjlCUtOHywlhYqs0cPx)