bofenghuang commited on
Commit
306c7f2
1 Parent(s): 1f093f5

Initial commit

Browse files
.gitignore ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ checkpoint-*/
2
+ *results.json
3
+ training_args.bin
4
+ trainer_state.json
5
+ normalizer.json
6
+ wer_summary/
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language: de
4
+ library_name: transformers
5
+ thumbnail: null
6
+ tags:
7
+ - automatic-speech-recognition
8
+ - whisper-event
9
+ datasets:
10
+ - mozilla-foundation/common_voice_11_0
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Fine-tuned whisper-large-v2 model for ASR in German
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice 11.0
21
+ type: mozilla-foundation/common_voice_11_0
22
+ config: de
23
+ split: test
24
+ args: de
25
+ metrics:
26
+ - name: WER (Greedy)
27
+ type: wer
28
+ value: 5.76
29
+ ---
30
+
31
+ <style>
32
+ img {
33
+ display: inline;
34
+ }
35
+ </style>
36
+
37
+ ![Model architecture](https://img.shields.io/badge/Model_Architecture-seq2seq-lightgrey)
38
+ ![Model size](https://img.shields.io/badge/Params-1550M-lightgrey)
39
+ ![Language](https://img.shields.io/badge/Language-German-lightgrey)
40
+
41
+ # Fine-tuned whisper-large-v2 model for ASR in German
42
+
43
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2), trained on the mozilla-foundation/common_voice_11_0 de dataset. When using the model make sure that your speech input is also sampled at 16Khz. **This model also predicts casing and punctuation.**
44
+
45
+ ## Usage
46
+
47
+ Inference with 🤗 Pipeline
48
+
49
+ ```python
50
+ import torch
51
+
52
+ from datasets import load_dataset
53
+ from transformers import pipeline
54
+
55
+ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
56
+
57
+ # Load pipeline
58
+ pipe = pipeline("automatic-speech-recognition", model="bofenghuang/whisper-large-v2-cv11-german-punct", device=device)
59
+
60
+ # NB: set forced_decoder_ids for generation utils
61
+ pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="de", task="transcribe")
62
+
63
+ # Load data
64
+ ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "de", split="test", streaming=True)
65
+ test_segment = next(iter(ds_mcv_test))
66
+ waveform = test_segment["audio"]
67
+
68
+ # NB: decoding option
69
+ # limit the maximum number of generated tokens to 225
70
+ pipe.model.config.max_length = 225 + 1
71
+ # sampling
72
+ # pipe.model.config.do_sample = True
73
+ # beam search
74
+ # pipe.model.config.num_beams = 5
75
+ # return
76
+ # pipe.model.config.return_dict_in_generate = True
77
+ # pipe.model.config.output_scores = True
78
+ # pipe.model.config.num_return_sequences = 5
79
+
80
+ # Run
81
+ generated_sentences = pipe(waveform)["text"]
82
+ ```
83
+
84
+ Inference with 🤗 low-level APIs
85
+
86
+ ```python
87
+ import torch
88
+ import torchaudio
89
+
90
+ from datasets import load_dataset
91
+ from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
92
+
93
+ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
94
+
95
+ # Load model
96
+ model = AutoModelForSpeechSeq2Seq.from_pretrained("bofenghuang/whisper-large-v2-cv11-german-punct").to(device)
97
+ processor = AutoProcessor.from_pretrained("bofenghuang/whisper-large-v2-cv11-german-punct", language="german", task="transcribe")
98
+
99
+ # NB: set forced_decoder_ids for generation utils
100
+ model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="de", task="transcribe")
101
+
102
+ # 16_000
103
+ model_sample_rate = processor.feature_extractor.sampling_rate
104
+
105
+ # Load data
106
+ ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "de", split="test", streaming=True)
107
+ test_segment = next(iter(ds_mcv_test))
108
+ waveform = torch.from_numpy(test_segment["audio"]["array"])
109
+ sample_rate = test_segment["audio"]["sampling_rate"]
110
+
111
+ # Resample
112
+ if sample_rate != model_sample_rate:
113
+ resampler = torchaudio.transforms.Resample(sample_rate, model_sample_rate)
114
+ waveform = resampler(waveform)
115
+
116
+ # Get feat
117
+ inputs = processor(waveform, sampling_rate=model_sample_rate, return_tensors="pt")
118
+ input_features = inputs.input_features
119
+ input_features = input_features.to(device)
120
+
121
+ # Generate
122
+ generated_ids = model.generate(inputs=input_features, max_new_tokens=225) # greedy
123
+ # generated_ids = model.generate(inputs=input_features, max_new_tokens=225, num_beams=5) # beam search
124
+
125
+ # Detokenize
126
+ generated_sentences = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
127
+
128
+ # Normalise predicted sentences if necessary
129
+ ```
added_tokens.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|af|>": 50327,
3
+ "<|am|>": 50334,
4
+ "<|ar|>": 50272,
5
+ "<|as|>": 50350,
6
+ "<|az|>": 50304,
7
+ "<|ba|>": 50355,
8
+ "<|be|>": 50330,
9
+ "<|bg|>": 50292,
10
+ "<|bn|>": 50302,
11
+ "<|bo|>": 50347,
12
+ "<|br|>": 50309,
13
+ "<|bs|>": 50315,
14
+ "<|ca|>": 50270,
15
+ "<|cs|>": 50283,
16
+ "<|cy|>": 50297,
17
+ "<|da|>": 50285,
18
+ "<|de|>": 50261,
19
+ "<|el|>": 50281,
20
+ "<|endoftext|>": 50257,
21
+ "<|en|>": 50259,
22
+ "<|es|>": 50262,
23
+ "<|et|>": 50307,
24
+ "<|eu|>": 50310,
25
+ "<|fa|>": 50300,
26
+ "<|fi|>": 50277,
27
+ "<|fo|>": 50338,
28
+ "<|fr|>": 50265,
29
+ "<|gl|>": 50319,
30
+ "<|gu|>": 50333,
31
+ "<|haw|>": 50352,
32
+ "<|ha|>": 50354,
33
+ "<|hi|>": 50276,
34
+ "<|hr|>": 50291,
35
+ "<|ht|>": 50339,
36
+ "<|hu|>": 50286,
37
+ "<|hy|>": 50312,
38
+ "<|id|>": 50275,
39
+ "<|is|>": 50311,
40
+ "<|it|>": 50274,
41
+ "<|iw|>": 50279,
42
+ "<|ja|>": 50266,
43
+ "<|jw|>": 50356,
44
+ "<|ka|>": 50329,
45
+ "<|kk|>": 50316,
46
+ "<|km|>": 50323,
47
+ "<|kn|>": 50306,
48
+ "<|ko|>": 50264,
49
+ "<|la|>": 50294,
50
+ "<|lb|>": 50345,
51
+ "<|ln|>": 50353,
52
+ "<|lo|>": 50336,
53
+ "<|lt|>": 50293,
54
+ "<|lv|>": 50301,
55
+ "<|mg|>": 50349,
56
+ "<|mi|>": 50295,
57
+ "<|mk|>": 50308,
58
+ "<|ml|>": 50296,
59
+ "<|mn|>": 50314,
60
+ "<|mr|>": 50320,
61
+ "<|ms|>": 50282,
62
+ "<|mt|>": 50343,
63
+ "<|my|>": 50346,
64
+ "<|ne|>": 50313,
65
+ "<|nl|>": 50271,
66
+ "<|nn|>": 50342,
67
+ "<|nocaptions|>": 50362,
68
+ "<|notimestamps|>": 50363,
69
+ "<|no|>": 50288,
70
+ "<|oc|>": 50328,
71
+ "<|pa|>": 50321,
72
+ "<|pl|>": 50269,
73
+ "<|ps|>": 50340,
74
+ "<|pt|>": 50267,
75
+ "<|ro|>": 50284,
76
+ "<|ru|>": 50263,
77
+ "<|sa|>": 50344,
78
+ "<|sd|>": 50332,
79
+ "<|si|>": 50322,
80
+ "<|sk|>": 50298,
81
+ "<|sl|>": 50305,
82
+ "<|sn|>": 50324,
83
+ "<|so|>": 50326,
84
+ "<|sq|>": 50317,
85
+ "<|sr|>": 50303,
86
+ "<|startoflm|>": 50360,
87
+ "<|startofprev|>": 50361,
88
+ "<|startoftranscript|>": 50258,
89
+ "<|su|>": 50357,
90
+ "<|sv|>": 50273,
91
+ "<|sw|>": 50318,
92
+ "<|ta|>": 50287,
93
+ "<|te|>": 50299,
94
+ "<|tg|>": 50331,
95
+ "<|th|>": 50289,
96
+ "<|tk|>": 50341,
97
+ "<|tl|>": 50348,
98
+ "<|transcribe|>": 50359,
99
+ "<|translate|>": 50358,
100
+ "<|tr|>": 50268,
101
+ "<|tt|>": 50351,
102
+ "<|uk|>": 50280,
103
+ "<|ur|>": 50290,
104
+ "<|uz|>": 50337,
105
+ "<|vi|>": 50278,
106
+ "<|yi|>": 50335,
107
+ "<|yo|>": 50325,
108
+ "<|zh|>": 50260
109
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large-v2",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 1280,
15
+ "decoder_attention_heads": 20,
16
+ "decoder_ffn_dim": 5120,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 32,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.05,
21
+ "encoder_attention_heads": 20,
22
+ "encoder_ffn_dim": 5120,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 32,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 32,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.26.0.dev0",
39
+ "use_cache": false,
40
+ "vocab_size": 51865
41
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10d90936368fbc11d8e23cbed4ed795129ec728f911b2579e27f4af58c51c85
3
+ size 3086784957
results_cv11_greedy/eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ WER: 0.05761999110428208
2
+ CER: 0.01686471998368856
results_cv11_greedy/log_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
results_cv11_greedy/log_targets.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec15_21-21-27_129-146-0-103/1671139337.3378797/events.out.tfevents.1671139337.129-146-0-103.1994026.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff71dadfdb1627b162c0835ad2b02ddcb9793c4914e4411786b70000f7c50ebe
3
+ size 6127
runs/Dec15_21-21-27_129-146-0-103/events.out.tfevents.1671139337.129-146-0-103.1994026.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0417271c6cc163963515a024ecb3d1f1400e462620fe8855e84b396dc540b44f
3
+ size 25611
runs/Dec15_21-21-27_129-146-0-103/events.out.tfevents.1671309779.129-146-0-103.1994026.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8937fc2447265df86427ba5688d2ac1923ca3d124a2b81f4940857d80dda6809
3
+ size 358
special_tokens_map.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|iw|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": "<|endoftext|>",
126
+ "unk_token": {
127
+ "content": "",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "openai/whisper-large-v2",
23
+ "pad_token": null,
24
+ "processor_class": "WhisperProcessor",
25
+ "return_attention_mask": false,
26
+ "special_tokens_map_file": null,
27
+ "tokenizer_class": "WhisperTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff