shhossain commited on
Commit
a5758dc
·
verified ·
1 Parent(s): 78d0f50

Upload processor

Browse files
README.md CHANGED
@@ -1,7 +1,16 @@
1
  ---
2
- base_model: patrickvonplaten/wav2vec2_tiny_random
 
 
 
3
  tags:
4
  - generated_from_trainer
 
 
 
 
 
 
5
  model-index:
6
  - name: wav2vec2-tiny-random-rodela-classifier
7
  results:
@@ -11,18 +20,9 @@ model-index:
11
  name: rodela_dataset
12
  type: test
13
  metrics:
14
- - name: accuracy
15
- type: accuracy
16
  value: 0.91
17
- datasets:
18
- - shhossain/rodela_dataset
19
- license: apache-2.0
20
- language:
21
- - en
22
- - bn
23
- metrics:
24
- - accuracy
25
- pipeline_tag: audio-classification
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
+ language:
3
+ - en
4
+ - bn
5
+ license: apache-2.0
6
  tags:
7
  - generated_from_trainer
8
+ datasets:
9
+ - shhossain/rodela_dataset
10
+ metrics:
11
+ - accuracy
12
+ base_model: patrickvonplaten/wav2vec2_tiny_random
13
+ pipeline_tag: audio-classification
14
  model-index:
15
  - name: wav2vec2-tiny-random-rodela-classifier
16
  results:
 
20
  name: rodela_dataset
21
  type: test
22
  metrics:
23
+ - type: accuracy
 
24
  value: 0.91
25
+ name: accuracy
 
 
 
 
 
 
 
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": false,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": false,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "7": {
4
+ "content": "<s>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "8": {
12
+ "content": "</s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "9": {
20
+ "content": "<unk>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "10": {
28
+ "content": "<pad>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 8,
3
+ "<pad>": 10,
4
+ "<s>": 7,
5
+ "<unk>": 9,
6
+ "a": 0,
7
+ "b": 1,
8
+ "c": 2,
9
+ "d": 3,
10
+ "e": 4,
11
+ "f": 5,
12
+ "g": 6,
13
+ "|": 11
14
+ }