oliverguhr commited on
Commit
c906292
1 Parent(s): 958455b

small lm added

Browse files
README.md CHANGED
@@ -24,7 +24,21 @@ model-index:
24
  value: 9.480663281840769
25
  - name: Test CER
26
  type: cer
27
- value: 2.273015898213336
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  - task:
29
  name: Automatic Speech Recognition
30
  type: automatic-speech-recognition
@@ -38,7 +52,21 @@ model-index:
38
  value: 8.122005951166668
39
  - name: Test CER
40
  type: cer
41
- value: 1.8815347657065468
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  ---
43
 
44
  # wav2vec2-large-xlsr-53-german-cv9
 
24
  value: 9.480663281840769
25
  - name: Test CER
26
  type: cer
27
+ value: 1.9167347943074394
28
+ - task:
29
+ name: Automatic Speech Recognition
30
+ type: automatic-speech-recognition
31
+ dataset:
32
+ name: Common Voice 9
33
+ type: mozilla-foundation/common_voice_9_0
34
+ args: de
35
+ metrics:
36
+ - name: Test WER
37
+ type: wer
38
+ value: 7.49027762774117
39
+ - name: Test CER
40
+ type: cer
41
+ value: 1.9167347943074394
42
  - task:
43
  name: Automatic Speech Recognition
44
  type: automatic-speech-recognition
 
52
  value: 8.122005951166668
53
  - name: Test CER
54
  type: cer
55
+ value: 1.
56
+ - task:
57
+ name: Automatic Speech Recognition
58
+ type: automatic-speech-recognition
59
+ dataset:
60
+ name: Common Voice 6.1
61
+ type: common_voice
62
+ args: de
63
+ metrics:
64
+ - name: Test WER (+LM)
65
+ type: wer
66
+ value: 6.1453182045203544
67
+ - name: Test CER (+LM)
68
+ type: cer
69
+ value: 1.5247743373447677
70
  ---
71
 
72
  # wav2vec2-large-xlsr-53-german-cv9
added_tokens.json CHANGED
@@ -1 +1,4 @@
1
- {"<s>": 33, "</s>": 34}
 
 
 
 
1
+ {
2
+ "</s>": 34,
3
+ "<s>": 33
4
+ }
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": [" ", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u00df", "\u00e4", "\u00f6", "\u00fc", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/5gram.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9282e9575d6f2b2853034f0695bd935c36b0262516578f9930c2c69a419a1146
3
+ size 315428505
language_model/attrs.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
language_model/unigrams.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json CHANGED
@@ -1 +1,36 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<s>",
33
+ "eos_token": "</s>",
34
+ "pad_token": "[PAD]",
35
+ "unk_token": "[UNK]"
36
+ }
tokenizer_config.json CHANGED
@@ -1 +1,13 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "./wav2vec2-large-xlsr-53-german-cv9", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "published/wav2vec2-large-xlsr-53-german-cv9",
6
+ "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json CHANGED
@@ -1 +1,35 @@
1
- {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "ß": 27, "ä": 28, "ö": 29, "ü": 30, "|": 0, "[UNK]": 31, "[PAD]": 32}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 32,
3
+ "[UNK]": 31,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "f": 6,
10
+ "g": 7,
11
+ "h": 8,
12
+ "i": 9,
13
+ "j": 10,
14
+ "k": 11,
15
+ "l": 12,
16
+ "m": 13,
17
+ "n": 14,
18
+ "o": 15,
19
+ "p": 16,
20
+ "q": 17,
21
+ "r": 18,
22
+ "s": 19,
23
+ "t": 20,
24
+ "u": 21,
25
+ "v": 22,
26
+ "w": 23,
27
+ "x": 24,
28
+ "y": 25,
29
+ "z": 26,
30
+ "|": 0,
31
+ "ß": 27,
32
+ "ä": 28,
33
+ "ö": 29,
34
+ "ü": 30
35
+ }