cahya commited on
Commit
423bd23
1 Parent(s): 96cbf24

added the files

Browse files
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: id
3
+ datasets:
4
+ - common_voice
5
+ metrics:
6
+ - wer
7
+ tags:
8
+ - audio
9
+ - automatic-speech-recognition
10
+ - speech
11
+ - xlsr-fine-tuning-week
12
+ license: apache-2.0
13
+ model-index:
14
+ - name: XLSR Wav2Vec2 Indonesian Mix by cahya
15
+ results:
16
+ - task:
17
+ name: Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice id
21
+ type: common_voice
22
+ args: id
23
+ metrics:
24
+ - name: Test WER
25
+ type: wer
26
+ value: 22.26
27
+ ---
28
+
29
+ # Wav2Vec2-Large-XLSR-Indonesian
30
+
31
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
32
+ on the [Indonesian Common Voice dataset](https://huggingface.co/datasets/common_voice) and synthetic voices
33
+ generated using [Artificial Common Voicer](https://github.com/cahya-wirawan/artificial-commonvoice), which
34
+ again based on Google Text To Speech.
35
+ When using this model, make sure that your speech input is sampled at 16kHz.
36
+
37
+ ## Usage
38
+ The model can be used directly (without a language model) as follows:
39
+ ```python
40
+ import torch
41
+ import torchaudio
42
+ from datasets import load_dataset
43
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
44
+
45
+ test_dataset = load_dataset("common_voice", "id", split="test[:2%]")
46
+
47
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-indonesian")
48
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-indonesian")
49
+
50
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
51
+
52
+ # Preprocessing the datasets.
53
+ # We need to read the aduio files as arrays
54
+ def speech_file_to_array_fn(batch):
55
+ \tspeech_array, sampling_rate = torchaudio.load(batch["path"])
56
+ \tbatch["speech"] = resampler(speech_array).squeeze().numpy()
57
+ \treturn batch
58
+
59
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
60
+ inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
61
+
62
+ with torch.no_grad():
63
+ \tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
64
+
65
+ predicted_ids = torch.argmax(logits, dim=-1)
66
+
67
+ print("Prediction:", processor.batch_decode(predicted_ids))
68
+ print("Reference:", test_dataset["sentence"][:2])
69
+ ```
70
+
71
+
72
+ ## Evaluation
73
+
74
+ The model can be evaluated as follows on the Indonesian test data of Common Voice.
75
+
76
+ ```python
77
+ import torch
78
+ import torchaudio
79
+ from datasets import load_dataset, load_metric
80
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
81
+ import re
82
+
83
+ test_dataset = load_dataset("common_voice", "id", split="test")
84
+ wer = load_metric("wer")
85
+
86
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-indonesian")
87
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-indonesian")
88
+ model.to("cuda")
89
+
90
+ chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\'\\”]'
91
+
92
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
93
+
94
+ # Preprocessing the datasets.
95
+ # We need to read the aduio files as arrays
96
+ def speech_file_to_array_fn(batch):
97
+ \tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
98
+ \tspeech_array, sampling_rate = torchaudio.load(batch["path"])
99
+ \tbatch["speech"] = resampler(speech_array).squeeze().numpy()
100
+ \treturn batch
101
+
102
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
103
+
104
+ # Preprocessing the datasets.
105
+ # We need to read the aduio files as arrays
106
+ def evaluate(batch):
107
+ \tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
108
+
109
+ \twith torch.no_grad():
110
+ \t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
111
+
112
+ pred_ids = torch.argmax(logits, dim=-1)
113
+ \tbatch["pred_strings"] = processor.batch_decode(pred_ids)
114
+ \treturn batch
115
+
116
+ result = test_dataset.map(evaluate, batched=True, batch_size=8)
117
+
118
+ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
119
+ ```
120
+
121
+ **Test Result**: 22.26 %
122
+
123
+ ## Training
124
+
125
+ The Common Voice `train`, `validation`, and ... datasets were used for training as well as ... and ... # TODO
126
+
127
+ The script used for training can be found [here](https://github.com/cahya-wirawan/indonesian-speech-recognition)
128
+ (will be available soon)
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./wav2vec2-large-xlsr-indonesian-articial-CV",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": true,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.3,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "num_attention_heads": 16,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 24,
73
+ "pad_token_id": 27,
74
+ "transformers_version": "4.4.0",
75
+ "vocab_size": 28
76
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da4553e639a15070f298127b138a18e4ecdd56ee5b189eb6a6a2086f20f9896
3
+ size 1262048600
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"n": 0, "f": 1, "b": 3, "p": 4, "v": 5, "g": 6, "r": 7, "m": 8, "t": 9, "h": 10, "c": 11, "a": 12, "z": 13, "l": 14, "u": 15, "i": 16, "s": 17, "k": 18, "y": 19, "e": 20, "w": 21, "x": 22, "d": 23, "j": 24, "o": 25, "|": 2, "[UNK]": 26, "[PAD]": 27}