Create README.md

README.md

@@ -0,0 +1,127 @@
+---
+language: lg
+datasets:
+- common_voice (train+validation+other[upvotes > downvotes])
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: Lucio XLSR Wav2Vec2 Large Luganda
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice lg
+      type: common_voice
+      args: lg
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 48.47 #TODO (IMPORTANT): replace {wer_result_on_test} with the WER error rate you achieved on the common_voice test set. It should be in the format XX.XX (don't add the % sign here). **Please** remember to fill out this value after you evaluated your model, so that your model appears on the leaderboard. If you fill out this model card before evaluating your model, please remember to edit the model card afterward to fill in your value
+---
+
+# Wav2Vec2-Large-XLSR-53-lg
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Luganda using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, using train, validation and other (if the example had more upvotes than downvotes), and taking the test data for validation as well as test.
+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", "lg", split="test[:2%]") 
+
+processor = Wav2Vec2Processor.from_pretrained("lucio/wav2vec2-large-xlsr-luganda") 
+model = Wav2Vec2ForCTC.from_pretrained("lucio/wav2vec2-large-xlsr-luganda")
+
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the audio 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 Luganda 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", "lg", split="test")
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("lucio/wav2vec2-large-xlsr-luganda") 
+model = Wav2Vec2ForCTC.from_pretrained("lucio/wav2vec2-large-xlsr-luganda")
+model.to("cuda")
+
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the audio 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 audio 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**: 48.47 %  # 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 `other` datasets were used for training, with the additional filter applied to remove `other` data that did not have more up votes than down votes. 
+
+The script used for training was just the `run_finetuning.py` script provided in OVHcloud's databuzzword/hf-wav2vec image.