|
--- |
|
language: ja |
|
datasets: |
|
- common_voice |
|
metrics: |
|
- wer |
|
- cer |
|
model-index: |
|
- name: wav2vec2-xls-r-300m finetuned on Japanese Hiragana with no word boundaries by Hyungshin Ryu of SLPlab |
|
results: |
|
- task: |
|
name: Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: Common Voice Japanese |
|
type: common_voice |
|
args: ja |
|
metrics: |
|
- name: Test WER |
|
type: wer |
|
value: 90.66 |
|
- name: Test CER |
|
type: cer |
|
value: 19.35 |
|
--- |
|
# Wav2Vec2-XLS-R-300M-Japanese-Hiragana |
|
Fine-tuned [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on Japanese Hiragana characters using the [Common Voice](https://huggingface.co/datasets/common_voice) and [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut). |
|
The sentence outputs do not contain word boundaries. Audio inputs should be sampled at 16kHz. |
|
## Usage |
|
The model can be used directly as follows: |
|
|
|
```python |
|
!pip install mecab-python3 |
|
!pip install unidic-lite |
|
!pip install pykakasi |
|
|
|
|
|
import torch |
|
import torchaudio |
|
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor |
|
from datasets import load_dataset, load_metric |
|
import pykakasi |
|
import MeCab |
|
import re |
|
|
|
|
|
# load datasets, processor, and model |
|
test_dataset = load_dataset("common_voice", "ja", split="test") |
|
wer = load_metric("wer") |
|
cer = load_metric("cer") |
|
PTM = "slplab/wav2vec2-xls-r-300m-japanese-hiragana" |
|
print("PTM:", PTM) |
|
processor = Wav2Vec2Processor.from_pretrained(PTM) |
|
model = Wav2Vec2ForCTC.from_pretrained(PTM) |
|
device = "cuda" |
|
model.to(device) |
|
|
|
|
|
# preprocess datasets |
|
wakati = MeCab.Tagger("-Owakati") |
|
kakasi = pykakasi.kakasi() |
|
chars_to_ignore_regex = "[ใ,ใ]" |
|
|
|
def speech_file_to_array_fn_hiragana_nospace(batch): |
|
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).strip() |
|
batch["sentence"] = ''.join([d['hira'] for d in kakasi.convert(batch["sentence"])]) |
|
speech_array, sampling_rate = torchaudio.load(batch["path"]) |
|
resampler = torchaudio.transforms.Resample(sampling_rate, 16000) |
|
batch["speech"] = resampler(speech_array).squeeze() |
|
|
|
return batch |
|
|
|
test_dataset = test_dataset.map(speech_file_to_array_fn_hiragana_nospace) |
|
|
|
|
|
#evaluate |
|
def evaluate(batch): |
|
inputs = processor(batch["speech"], sampling_rate=16000, return_tensors="pt", padding=True) |
|
with torch.no_grad(): |
|
logits = model(inputs.input_values.to(device)).logits |
|
pred_ids = torch.argmax(logits, dim=-1) |
|
batch["pred_strings"] = processor.batch_decode(pred_ids) |
|
|
|
return batch |
|
|
|
result = test_dataset.map(evaluate, batched=True, batch_size=8) |
|
for i in range(10): |
|
print("="*20) |
|
print("Prd:", result[i]["pred_strings"]) |
|
print("Ref:", result[i]["sentence"]) |
|
|
|
print("WER: {:2f}%".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"]))) |
|
print("CER: {:2f}%".format(100 * cer.compute(predictions=result["pred_strings"], references=result["sentence"]))) |
|
``` |
|
| Original Text | Prediction | |
|
| ------------- | ------------- | |
|
| ใใฎๆ็ใฏๅฎถๅบญใงไฝใใพใใ | ใใฎใใใใใฏใใฆใใงใคใใใพใ | |
|
| ๆฅๆฌไบบใฏใๆฑบใใฆใใฆใผใขใขใจ็ก็ธใชไบบ็จฎใงใฏใชใใฃใใ | ใซใฃใฝใใใใฏใใใฆใใใใใฉใใใใชใใใใ
ใงใฏใชใใฃใ | |
|
| ๆจๆใใใซ้ป่ฉฑใ่ฒธใใฆใใใใพใใใ | ใใใใใใซใงใใใใใใฆใใใใพใใ | |
|
|
|
## Test Results |
|
**WER:** 90.66%, |
|
**CER:** 19.35% |
|
## Training |
|
Trained on JSUT and train+valid set of Common Voice Japanese. Tested on test set of Common Voice Japanese. |