patrickvonplaten
commited on
Commit
•
14766fd
1
Parent(s):
7c06399
Update README.md
Browse files
README.md
CHANGED
@@ -1,125 +1,4 @@
|
|
1 |
-
|
2 |
-
language: tr
|
3 |
-
datasets:
|
4 |
-
- common_voice
|
5 |
-
tags:
|
6 |
-
- audio
|
7 |
-
- automatic-speech-recognition
|
8 |
-
- speech
|
9 |
-
- xlsr-fine-tuning-week
|
10 |
-
license: apache-2.0
|
11 |
-
model-index:
|
12 |
-
- name: XLSR Wav2Vec2 Turkish by Patrick von Platen
|
13 |
-
results:
|
14 |
-
- task:
|
15 |
-
name: Speech Recognition
|
16 |
-
type: automatic-speech-recognition
|
17 |
-
dataset:
|
18 |
-
name: Common Voice tr
|
19 |
-
type: common_voice
|
20 |
-
args: {lang_id}
|
21 |
-
metrics:
|
22 |
-
- name: Test WER
|
23 |
-
type: wer
|
24 |
-
value: 37.1
|
25 |
-
---
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Turkish using the [Common Voice](https://huggingface.co/datasets/common_voice)
|
30 |
-
When using this model, make sure that your speech input is sampled at 16kHz.
|
31 |
-
|
32 |
-
## Usage
|
33 |
-
|
34 |
-
The model can be used directly (without a language model) as follows:
|
35 |
-
|
36 |
-
```python
|
37 |
-
import torch
|
38 |
-
import torchaudio
|
39 |
-
from datasets import load_dataset
|
40 |
-
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
41 |
-
|
42 |
-
test_dataset = load_dataset("common_voice", "tr", split="test[:2%]").
|
43 |
-
|
44 |
-
processor = Wav2Vec2Processor.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-turkish-demo")
|
45 |
-
model = Wav2Vec2ForCTC.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-turkish-demo")
|
46 |
-
|
47 |
-
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
48 |
-
|
49 |
-
# Preprocessing the datasets.
|
50 |
-
# We need to read the aduio files as arrays
|
51 |
-
def speech_file_to_array_fn(batch):
|
52 |
-
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
53 |
-
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
54 |
-
return batch
|
55 |
-
|
56 |
-
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
57 |
-
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
58 |
-
|
59 |
-
with torch.no_grad():
|
60 |
-
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
61 |
-
|
62 |
-
predicted_ids = torch.argmax(logits, dim=-1)
|
63 |
-
|
64 |
-
print("Prediction:", processor.batch_decode(predicted_ids))
|
65 |
-
print("Reference:", test_dataset["sentence"][:2])
|
66 |
-
```
|
67 |
-
|
68 |
-
|
69 |
-
## Evaluation
|
70 |
-
|
71 |
-
The model can be evaluated as follows on the {language} test data of Common Voice.
|
72 |
-
|
73 |
-
|
74 |
-
```python
|
75 |
-
import torch
|
76 |
-
import torchaudio
|
77 |
-
from datasets import load_dataset, load_metric
|
78 |
-
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
79 |
-
import re
|
80 |
-
|
81 |
-
test_dataset = load_dataset("common_voice", "tr", split="test")
|
82 |
-
wer = load_metric("wer")
|
83 |
-
|
84 |
-
processor = Wav2Vec2Processor.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-turkish-demo")
|
85 |
-
model = Wav2Vec2ForCTC.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-turkish-demo")
|
86 |
-
model.to("cuda")
|
87 |
-
|
88 |
-
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
|
89 |
-
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
90 |
-
|
91 |
-
# Preprocessing the datasets.
|
92 |
-
# We need to read the aduio files as arrays
|
93 |
-
def speech_file_to_array_fn(batch):
|
94 |
-
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
95 |
-
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
96 |
-
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
97 |
-
return batch
|
98 |
-
|
99 |
-
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
100 |
-
|
101 |
-
# Preprocessing the datasets.
|
102 |
-
# We need to read the aduio files as arrays
|
103 |
-
def evaluate(batch):
|
104 |
-
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
105 |
-
|
106 |
-
with torch.no_grad():
|
107 |
-
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
|
108 |
-
|
109 |
-
pred_ids = torch.argmax(logits, dim=-1)
|
110 |
-
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
111 |
-
return batch
|
112 |
-
|
113 |
-
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
114 |
-
|
115 |
-
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
116 |
-
```
|
117 |
-
|
118 |
-
**Test Result**: 37.10 %
|
119 |
-
|
120 |
-
|
121 |
-
## Training
|
122 |
-
|
123 |
-
The Common Voice `train`, `validation` datasets were used for training.
|
124 |
-
|
125 |
-
The script used for training can be found [here](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLSR_Wav2Vec2_on_Turkish_ASR_with_%F0%9F%A4%97_Transformers.ipynb)
|
1 |
+
## Wav2Vec2 Fine-Tuned on English dataset Timit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
+
The model was fine-tuned in a google colab for demonstration purposes.
|
4 |
+
Please refer to [this blog](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) for more information about the model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|