Update README.md

README.md

@@ -8,14 +8,118 @@ tags:
 - speech
 - xlsr-fine-tuning-week
 license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Swedish by Birger Moell
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice sv-SE
+      type: common_voice
+      args: sv-SE 
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 36.91
 ---
 
-## wav2vec2-swedish-common-voice
-This model is fine-tuned from Facebook's wav2vec2-large-xlsr-53 using Mozilla's common voice dataset. 
-Wav2vec2-swedish trained on the common voice dataset.
+# Wav2Vec2-Large-XLSR-53-Swedish
 
-## Model metric
-WER 0.3691 on a dataset of 402mb.
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Swedish using the [Common Voice](https://huggingface.co/datasets/common_voice). The training data amounts to 402 MB.
+When using this model, make sure that your speech input is sampled at 16kHz.
 
-## Model Fine-Tuning-Colab
-https://colab.research.google.com/drive/1KkD4PeZwnIwxxxOP1bUE7XTZMK7-SzRj?usp=sharing
+## 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", "sv-SE", split="test[:2%]").
+
+processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-swedish-common-voice")
+model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-swedish-common-voice")
+
+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.
+
+
+```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", "sv-SE", split="test")
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-swedish-common-voice")
+model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-swedish-common-voice")
+model.to("cuda")
+
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+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**: 36.91 %
+
+
+## Training
+
+The Common Voice `train`, `validation` datasets were used for training.
+
+The script used for training can be found [here](https://colab.research.google.com/drive/1KkD4PeZwnIwxxxOP1bUE7XTZMK7-SzRj?usp=sharing)