ivangtorre
commited on
Commit
•
5a40a3e
1
Parent(s):
6049946
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,109 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-4.0
|
3 |
+
language:
|
4 |
+
- gvc
|
5 |
+
metrics:
|
6 |
+
- cer
|
7 |
+
pipeline_tag: automatic-speech-recognition
|
8 |
+
datasets:
|
9 |
+
- ivangtorre/second_americas_nlp_2022
|
10 |
+
tags:
|
11 |
+
- audio
|
12 |
+
- automatic-speech-recognition
|
13 |
+
- speech
|
14 |
+
- kotiria
|
15 |
+
- xlsr-fine-tuning
|
16 |
+
model-index:
|
17 |
+
- name: Wav2Vec2 XLSR 300M Kotiria Model by M Romero and Ivan G Torre
|
18 |
+
results:
|
19 |
+
- task:
|
20 |
+
name: Speech Recognition
|
21 |
+
type: automatic-speech-recognition
|
22 |
+
dataset:
|
23 |
+
name: Americas NLP 2022 Kotiria
|
24 |
+
type: second_americas_nlp_2022
|
25 |
+
args: Kotiria
|
26 |
+
metrics:
|
27 |
+
- name: Test CER
|
28 |
+
type: cer
|
29 |
+
value: 36.00
|
30 |
+
|
31 |
+
---
|
32 |
+
|
33 |
+
This model was finetuned from a Wav2vec2.0 XLS-R model: 300M with the Kotiria train parition of the Americas NLP 2022 dataset. This challenge took place during NeurIPSS 2022.
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
## Example of usage
|
38 |
+
|
39 |
+
The model can be used directly (without a language model) as follows:
|
40 |
+
|
41 |
+
```python
|
42 |
+
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
|
43 |
+
import torch
|
44 |
+
import torchaudio
|
45 |
+
|
46 |
+
# load model and processor
|
47 |
+
processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-kotiria")
|
48 |
+
model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-kotiria")
|
49 |
+
|
50 |
+
# Pat to wav file
|
51 |
+
pathfile = "/path/to/wavfile"
|
52 |
+
|
53 |
+
# Load and normalize the file
|
54 |
+
wav, curr_sample_rate = sf.read(pathfile, dtype="float32")
|
55 |
+
feats = torch.from_numpy(wav).float()
|
56 |
+
with torch.no_grad():
|
57 |
+
feats = F.layer_norm(feats, feats.shape)
|
58 |
+
feats = torch.unsqueeze(feats, 0)
|
59 |
+
logits = model(feats).logits
|
60 |
+
|
61 |
+
# take argmax and decode
|
62 |
+
predicted_ids = torch.argmax(logits, dim=-1)
|
63 |
+
transcription = processor.batch_decode(predicted_ids)
|
64 |
+
print("HF prediction: ", transcription)
|
65 |
+
```
|
66 |
+
|
67 |
+
|
68 |
+
This code snipnet shows how to Evaluate the wav2vec2-xlsr-300m-kotiria in [Second Americas NLP 2022 Kotiria dev set](https://huggingface.co/datasets/ivangtorre/second_americas_nlp_2022)
|
69 |
+
|
70 |
+
```python
|
71 |
+
from datasets import load_dataset
|
72 |
+
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
73 |
+
import torch
|
74 |
+
from jiwer import cer
|
75 |
+
import torch.nn.functional as F
|
76 |
+
from datasets import load_dataset
|
77 |
+
import soundfile as sf
|
78 |
+
|
79 |
+
americasnlp = load_dataset("ivangtorre/second_americas_nlp_2022", "kotiria", split="dev")
|
80 |
+
kotiria = americasnlp.filter(lambda language: language['subset']=='kotiria')
|
81 |
+
|
82 |
+
model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-kotiria")
|
83 |
+
processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-kotiria")
|
84 |
+
|
85 |
+
def map_to_pred(batch):
|
86 |
+
wav = batch["audio"][0]["array"]
|
87 |
+
feats = torch.from_numpy(wav).float()
|
88 |
+
feats = F.layer_norm(feats, feats.shape) # Normalization performed during finetuning
|
89 |
+
feats = torch.unsqueeze(feats, 0)
|
90 |
+
logits = model(feats).logits
|
91 |
+
predicted_ids = torch.argmax(logits, dim=-1)
|
92 |
+
batch["transcription"] = processor.batch_decode(predicted_ids)
|
93 |
+
return batch
|
94 |
+
|
95 |
+
result = kotiria.map(map_to_pred, batched=True, batch_size=1)
|
96 |
+
|
97 |
+
print("CER:", cer(result["source_processed"], result["transcription"]))
|
98 |
+
```
|
99 |
+
|
100 |
+
## Citation
|
101 |
+
|
102 |
+
```bibtex
|
103 |
+
@article{romero2024asr,
|
104 |
+
title={ASR advancements for indigenous languages: Quechua, Guarani, Bribri, Kotiria, and Wa'ikhana},
|
105 |
+
author={Romero, Monica and Gomez, Sandra and Torre, Iv{\'a}n G},
|
106 |
+
journal={arXiv preprint arXiv:2404.08368},
|
107 |
+
year={2024}
|
108 |
+
}
|
109 |
+
```
|