Upload tokenizer
Browse files- README.md +3 -3
- tokenizer_config.json +1 -0
README.md
CHANGED
@@ -12,8 +12,8 @@ model-index:
|
|
12 |
- name: wav2vec2-large-xls-r-300m-vi-colab
|
13 |
results:
|
14 |
- task:
|
15 |
-
name: Automatic Speech Recognition
|
16 |
type: automatic-speech-recognition
|
|
|
17 |
dataset:
|
18 |
name: common_voice_17_0
|
19 |
type: common_voice_17_0
|
@@ -21,9 +21,9 @@ model-index:
|
|
21 |
split: test
|
22 |
args: vi
|
23 |
metrics:
|
24 |
-
-
|
25 |
-
type: wer
|
26 |
value: 0.5489199491740788
|
|
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
12 |
- name: wav2vec2-large-xls-r-300m-vi-colab
|
13 |
results:
|
14 |
- task:
|
|
|
15 |
type: automatic-speech-recognition
|
16 |
+
name: Automatic Speech Recognition
|
17 |
dataset:
|
18 |
name: common_voice_17_0
|
19 |
type: common_voice_17_0
|
|
|
21 |
split: test
|
22 |
args: vi
|
23 |
metrics:
|
24 |
+
- type: wer
|
|
|
25 |
value: 0.5489199491740788
|
26 |
+
name: Wer
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
tokenizer_config.json
CHANGED
@@ -37,6 +37,7 @@
|
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"do_lower_case": false,
|
39 |
"eos_token": "</s>",
|
|
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
"replace_word_delimiter_char": " ",
|
|
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"do_lower_case": false,
|
39 |
"eos_token": "</s>",
|
40 |
+
"extra_special_tokens": {},
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
"pad_token": "[PAD]",
|
43 |
"replace_word_delimiter_char": " ",
|