Update README.md

README.md

@@ -18,55 +18,76 @@ model-index:
     dataset:
       name: Common Voice ta
       type: common_voice
-      args: {lang_id}  
+      args: ta 
     metrics:
        - name: Test WER
          type: wer
-         value: 0.7071799915694815
+         value: 70.72
 ---
 # Wav2Vec2-Large-XLSR-53-tamil
+
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Tamil using the [Common Voice](https://huggingface.co/datasets/common_voice)
+
 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", "tr", split="test[:2%]").
+
+test_dataset = load_dataset("common_voice", "tr", split="test[:2%]")
+
 processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
 model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
+
 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", "tr", split="test")
+
 wer = load_metric("wer")
+
 processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
 model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
+
 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):
@@ -74,17 +95,21 @@ 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)
+
 # 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)
+    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.compute(predictions=result["predicted"], references=result["target"]))
 ```
-**Test Result**: 0.7071799915694815
+
+**Test Result**: 70.72 %