DewiBrynJones
commited on
Commit
•
6d521d8
1
Parent(s):
f4d2d65
gwella'r WER
Browse files- README.md +2 -2
- config.json +6 -6
- pytorch_model.bin +2 -2
- vocab.json +1 -1
README.md
CHANGED
@@ -23,7 +23,7 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
-
value:
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-Welsh
|
@@ -122,7 +122,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
|
122 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
123 |
```
|
124 |
|
125 |
-
**Test Result**:
|
126 |
|
127 |
|
128 |
# Training
|
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
+
value: 25.31
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-Welsh
|
|
|
122 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
123 |
```
|
124 |
|
125 |
+
**Test Result**: 25.31%
|
126 |
|
127 |
|
128 |
# Training
|
config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
-
"activation_dropout": 0.
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
7 |
],
|
8 |
-
"attention_dropout": 0.
|
9 |
"bos_token_id": 1,
|
10 |
"conv_bias": true,
|
11 |
"conv_dim": [
|
@@ -42,16 +42,16 @@
|
|
42 |
"feat_extract_activation": "gelu",
|
43 |
"feat_extract_dropout": 0.0,
|
44 |
"feat_extract_norm": "layer",
|
45 |
-
"feat_proj_dropout": 0.
|
46 |
"final_dropout": 0.0,
|
47 |
"gradient_checkpointing": true,
|
48 |
"hidden_act": "gelu",
|
49 |
-
"hidden_dropout": 0.
|
50 |
"hidden_size": 1024,
|
51 |
"initializer_range": 0.02,
|
52 |
"intermediate_size": 4096,
|
53 |
"layer_norm_eps": 1e-05,
|
54 |
-
"layerdrop": 0.
|
55 |
"mask_channel_length": 10,
|
56 |
"mask_channel_min_space": 1,
|
57 |
"mask_channel_other": 0.0,
|
@@ -62,7 +62,7 @@
|
|
62 |
"mask_time_length": 10,
|
63 |
"mask_time_min_space": 1,
|
64 |
"mask_time_other": 0.0,
|
65 |
-
"mask_time_prob": 0.
|
66 |
"mask_time_selection": "static",
|
67 |
"model_type": "wav2vec2",
|
68 |
"num_attention_heads": 16,
|
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.055,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
7 |
],
|
8 |
+
"attention_dropout": 0.094,
|
9 |
"bos_token_id": 1,
|
10 |
"conv_bias": true,
|
11 |
"conv_dim": [
|
|
|
42 |
"feat_extract_activation": "gelu",
|
43 |
"feat_extract_dropout": 0.0,
|
44 |
"feat_extract_norm": "layer",
|
45 |
+
"feat_proj_dropout": 0.04,
|
46 |
"final_dropout": 0.0,
|
47 |
"gradient_checkpointing": true,
|
48 |
"hidden_act": "gelu",
|
49 |
+
"hidden_dropout": 0.047,
|
50 |
"hidden_size": 1024,
|
51 |
"initializer_range": 0.02,
|
52 |
"intermediate_size": 4096,
|
53 |
"layer_norm_eps": 1e-05,
|
54 |
+
"layerdrop": 0.041,
|
55 |
"mask_channel_length": 10,
|
56 |
"mask_channel_min_space": 1,
|
57 |
"mask_channel_other": 0.0,
|
|
|
62 |
"mask_time_length": 10,
|
63 |
"mask_time_min_space": 1,
|
64 |
"mask_time_other": 0.0,
|
65 |
+
"mask_time_prob": 0.082,
|
66 |
"mask_time_selection": "static",
|
67 |
"model_type": "wav2vec2",
|
68 |
"num_attention_heads": 16,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b3d1d4c5339a82fac76d5a361323ba7c8e8faa278c8f37e1e4db9929ecd4705
|
3 |
+
size 1262129841
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"g": 1, "‘": 2, "e": 3, "r": 4, "b": 5, "ê": 6, "â": 7, "ŷ": 8, "'": 9, "v": 10, "ö": 11, "ï": 12, "h": 13, "z": 14, "m": 15, "á": 16, "ä": 17, "ñ": 18, "o": 19, "n": 20, "j": 21, "ò": 22, "ë": 23, "î": 24, "k": 25, "q": 26, "x": 27, "¬": 28, "a": 29, "s": 30, "i": 31, "ÿ": 32, "u": 33, "ŵ": 34, "c": 35, "é": 36, "w": 37, "p": 38, "y": 39, "d": 40, "l": 41, "à": 42, "û": 43, "t": 44, "f": 45, "ô": 46, "|": 0, "[UNK]": 47, "[PAD]": 48}
|