Update app.py
Browse files
app.py
CHANGED
|
@@ -36,21 +36,19 @@ def dịch(text: str, file_obj: str, batch_size: int, progress=gr.Progress()) ->
|
|
| 36 |
if file_obj is not None:
|
| 37 |
with open(file_obj, "r", encoding="utf-8", errors="ignore") as f:
|
| 38 |
text = f.read()
|
| 39 |
-
if text.strip() == "":
|
| 40 |
-
return ""
|
| 41 |
|
| 42 |
inputs = []
|
| 43 |
for line in text.split("\n"):
|
| 44 |
if (l := line.strip()) != "":
|
| 45 |
inputs.append(TOKENIZER.convert_ids_to_tokens(TOKENIZER.encode(l, truncation=True)))
|
| 46 |
|
| 47 |
-
if
|
| 48 |
return ""
|
| 49 |
|
| 50 |
results = []
|
| 51 |
for i in progress.tqdm(range(0, len(inputs), batch_size)):
|
| 52 |
outputs = TRANSLATOR.translate_batch(
|
| 53 |
-
inputs,
|
| 54 |
max_decoding_length=TOKENIZER.model_max_length,
|
| 55 |
max_batch_size=batch_size,
|
| 56 |
beam_size=4,
|
|
|
|
| 36 |
if file_obj is not None:
|
| 37 |
with open(file_obj, "r", encoding="utf-8", errors="ignore") as f:
|
| 38 |
text = f.read()
|
|
|
|
|
|
|
| 39 |
|
| 40 |
inputs = []
|
| 41 |
for line in text.split("\n"):
|
| 42 |
if (l := line.strip()) != "":
|
| 43 |
inputs.append(TOKENIZER.convert_ids_to_tokens(TOKENIZER.encode(l, truncation=True)))
|
| 44 |
|
| 45 |
+
if len(inputs) == 0:
|
| 46 |
return ""
|
| 47 |
|
| 48 |
results = []
|
| 49 |
for i in progress.tqdm(range(0, len(inputs), batch_size)):
|
| 50 |
outputs = TRANSLATOR.translate_batch(
|
| 51 |
+
inputs[i : i + batch_size],
|
| 52 |
max_decoding_length=TOKENIZER.model_max_length,
|
| 53 |
max_batch_size=batch_size,
|
| 54 |
beam_size=4,
|