fix incorrect in usage/evaluate
Browse files
README.md
CHANGED
@@ -59,7 +59,7 @@ def speech_file_to_array_fn(batch):
|
|
59 |
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
60 |
return batch
|
61 |
|
62 |
-
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
63 |
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
64 |
|
65 |
with torch.no_grad():
|
@@ -122,7 +122,7 @@ def evaluate(batch):
|
|
122 |
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
123 |
return batch
|
124 |
|
125 |
-
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
126 |
|
127 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
128 |
```
|
|
|
59 |
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
60 |
return batch
|
61 |
|
62 |
+
test_dataset = test_dataset.map(speech_file_to_array_fn).map(th_tokenize)
|
63 |
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
64 |
|
65 |
with torch.no_grad():
|
|
|
122 |
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
123 |
return batch
|
124 |
|
125 |
+
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
126 |
|
127 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
128 |
```
|