update eval script

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 70.72
+         value: 69.76
 ---
 # Wav2Vec2-Large-XLSR-53-tamil
 
@@ -49,16 +49,16 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # We need to read the aduio files as arrays
 
 def speech_file_to_array_fn(batch):
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\treturn batch
-\t
+\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\\treturn batch
+\\t
 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():
-\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
-\t
+\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+\\t
 predicted_ids = torch.argmax(logits, dim=-1)
 print("Prediction:", processor.batch_decode(predicted_ids))
 print("Reference:", test_dataset["sentence"][:2])
@@ -79,8 +79,8 @@ test_dataset = load_dataset("common_voice", "ta", split="test")
 
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
-model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-tamil")
+processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")
+model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")
 
 model.to("cuda")
 chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'
@@ -90,25 +90,25 @@ 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):
-\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\treturn batch
-\t
+    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):
-\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
-\twith torch.no_grad():
-\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+    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)
-\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\treturn batch
-\t
+    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["predicted"], references=result["target"])))
+print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 
-**Test Result**: 70.72 %
+**Test Result**: 69.76 %