Update README.md

README.md

@@ -29,61 +29,51 @@ 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%]").
-processor = Wav2Vec2Processor.from_pretrained("akashpb13/wav2vec2-large-xlsr-Maltese")
-model = Wav2Vec2ForCTC.from_pretrained("akashpb13/wav2vec2-large-xlsr-Maltese")
-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
+from transformers import (
+    Wav2Vec2ForCTC,
+    Wav2Vec2Processor,
+)
+import torch
 import re
-test_dataset = load_dataset("common_voice", "mt", split="test")
-wer = load_metric("wer")
-processor = Wav2Vec2Processor.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-Maltese-demo")
-model = Wav2Vec2ForCTC.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-Maltese-demo")
-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
+import sys
+
+model_name = "Akashpb13/xlsr_maltese_wav2vec2"
+device = "cuda"
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\)\(\*)]'
+
+model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
+processor = Wav2Vec2Processor.from_pretrained(model_name)
+
+ds = load_dataset("common_voice", "mt", split="test", data_dir="./cv-corpus-6.1-2020-12-11")
+
+resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)
+
+def map_to_array(batch):
+    speech, _ = torchaudio.load(batch["path"])
+    batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
+    batch["sampling_rate"] = resampler.new_freq
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
+    return batch
+
+ds = ds.map(map_to_array)
+
+def map_to_pred(batch):
+    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
+    input_values = features.input_values.to(device)
+    attention_mask = features.attention_mask.to(device)
+    with torch.no_grad():
+        logits = model(input_values, attention_mask=attention_mask).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"])))
+    batch["predicted"] = processor.batch_decode(pred_ids)
+    batch["target"] = batch["sentence"]
+    return batch
+
+result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys()))
+
+wer = load_metric("wer")
+print(wer.compute(predictions=result["predicted"], references=result["target"]))
+
 ```
-**Test Result**: 32.77 %
+**Test Result**: 32.83 %