Commit
·
261c60f
1
Parent(s):
5859a7b
Upload gec_model.py (#1)
Browse files- Upload gec_model.py (a054769d1cd4d149db1357e29ff211fb4186ecf5)
Co-authored-by: An Thành Long <Cnydo@users.noreply.huggingface.co>
- gec_model.py +1 -1
gec_model.py
CHANGED
|
@@ -89,11 +89,11 @@ class GecBERTModel(torch.nn.Module):
|
|
| 89 |
self.lowercase_tokens = lowercase_tokens
|
| 90 |
self.min_error_probability = min_error_probability
|
| 91 |
self.vocab = Vocabulary.from_files(vocab_path)
|
|
|
|
| 92 |
self.log = log
|
| 93 |
self.iterations = iterations
|
| 94 |
self.confidence = confidence
|
| 95 |
self.resolve_cycles = resolve_cycles
|
| 96 |
-
|
| 97 |
assert (
|
| 98 |
chunk_size > 0 and chunk_size // 2 >= overlap_size
|
| 99 |
), "Chunk merging required overlap size must be smaller than half of chunk size"
|
|
|
|
| 89 |
self.lowercase_tokens = lowercase_tokens
|
| 90 |
self.min_error_probability = min_error_probability
|
| 91 |
self.vocab = Vocabulary.from_files(vocab_path)
|
| 92 |
+
self.incorr_index = self.vocab.get_token_index("INCORRECT", "d_tags")
|
| 93 |
self.log = log
|
| 94 |
self.iterations = iterations
|
| 95 |
self.confidence = confidence
|
| 96 |
self.resolve_cycles = resolve_cycles
|
|
|
|
| 97 |
assert (
|
| 98 |
chunk_size > 0 and chunk_size // 2 >= overlap_size
|
| 99 |
), "Chunk merging required overlap size must be smaller than half of chunk size"
|