|
--- |
|
language: zh |
|
datasets: |
|
- common_voice |
|
tags: |
|
- audio |
|
- automatic-speech-recognition |
|
- speech |
|
- xlsr-fine-tuning-week |
|
license: apache-2.0 |
|
model-index: |
|
- name: XLSR Wav2Vec2 Chinese (Taiwan) by Voidful |
|
results: |
|
- task: |
|
name: Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: Common Voice zh-TW |
|
type: common_voice |
|
args: zh-TW |
|
metrics: |
|
- name: Test CER |
|
type: cer |
|
value: 78.03 |
|
--- |
|
|
|
## Colab trial with recording or voice file |
|
[Colab trial](https://colab.research.google.com/drive/1e_z5jQHYbO2YKEaUgzb1ww1WwiAyydAj?usp=sharing) |
|
|
|
``` |
|
import torchaudio |
|
from datasets import load_dataset, load_metric |
|
from transformers import ( |
|
Wav2Vec2ForCTC, |
|
Wav2Vec2Processor, |
|
AutoTokenizer, |
|
AutoModelWithLMHead |
|
) |
|
import torch |
|
import re |
|
import sys |
|
|
|
model_name = "voidful/wav2vec2-large-xlsr-53-tw-gpt" |
|
device = "cuda" |
|
processor_name = "voidful/wav2vec2-large-xlsr-53-tw-gpt" |
|
|
|
chars_to_ignore_regex = r"[¥•＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､ 、〃〈〉《》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏﹑﹔·'℃°•·．﹑︰〈〉─《﹖﹣﹂﹁﹔！？｡。＂＃＄％＆＇（）＊＋，﹐－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏.．!\"#$%&()*+,\-.\:;<=>?@\[\]\\\/^_`{|}~]" |
|
|
|
model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device) |
|
processor = Wav2Vec2Processor.from_pretrained(processor_name) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ckiplab/gpt2-base-chinese") |
|
gpt_model = AutoModelWithLMHead.from_pretrained("ckiplab/gpt2-base-chinese").to(device) |
|
|
|
resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000) |
|
|
|
def load_file_to_data(file): |
|
batch = {} |
|
speech, _ = torchaudio.load(file) |
|
batch["speech"] = resampler.forward(speech.squeeze(0)).numpy() |
|
batch["sampling_rate"] = resampler.new_freq |
|
return batch |
|
|
|
def predict(data): |
|
features = processor(data["speech"], sampling_rate=data["sampling_rate"], padding=True, return_tensors="pt") |
|
input_values = features.input_values.to(device) |
|
attention_mask = features.attention_mask.to(device) |
|
with torch.no_grad(): |
|
logits = model(input_values, attention_mask=attention_mask).logits |
|
|
|
decoded_results = [] |
|
for logit in logits: |
|
pred_ids = torch.argmax(logit, dim=-1) |
|
mask = pred_ids.ge(1).unsqueeze(-1).expand(logit.size()) |
|
vocab_size = logit.size()[-1] |
|
voice_prob = torch.nn.functional.softmax((torch.masked_select(logit, mask).view(-1,vocab_size)),dim=-1) |
|
gpt_input = torch.cat((torch.tensor([tokenizer.cls_token_id]).to(device),pred_ids[pred_ids>0]), 0) |
|
gpt_prob = torch.nn.functional.softmax(gpt_model(gpt_input).logits, dim=-1)[:voice_prob.size()[0],:] |
|
comb_pred_ids = torch.argmax(gpt_prob*voice_prob, dim=-1) |
|
decoded_results.append(processor.decode(comb_pred_ids)) |
|
|
|
return decoded_results |
|
``` |
|
|
|
Predict |
|
```python |
|
predict(load_file_to_data('voice file path')) |
|
``` |
|
|
|
## Evaluation on Common Voice TW Test |
|
```python |
|
import torchaudio |
|
from datasets import load_dataset, load_metric |
|
from transformers import ( |
|
Wav2Vec2ForCTC, |
|
Wav2Vec2Processor, |
|
) |
|
import torch |
|
import re |
|
|
|
model_name = "voidful/wav2vec2-large-xlsr-53-tw" |
|
device = "cuda" |
|
processor_name = "voidful/wav2vec2-large-xlsr-53-tw" |
|
|
|
chars_to_ignore_regex = r"[¥•＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､ 、〃〈〉《》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏﹑﹔·'℃°•·．﹑︰〈〉─《﹖﹣﹂﹁﹔！？｡。＂＃＄％＆＇（）＊＋，﹐－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏.．!\"#$%&()*+,\-.\:;<=>?@\[\]\\\/^_`{|}~]" |
|
|
|
model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device) |
|
processor = Wav2Vec2Processor.from_pretrained(processor_name) |
|
|
|
ds = load_dataset("common_voice", 'zh-TW', data_dir="./cv-corpus-6.1-2020-12-11", split="test") |
|
|
|
resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000) |
|
|
|
def map_to_array(batch): |
|
speech, _ = torchaudio.load(batch["path"]) |
|
batch["speech"] = resampler.forward(speech.squeeze(0)).numpy() |
|
batch["sampling_rate"] = resampler.new_freq |
|
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'") |
|
return batch |
|
|
|
ds = ds.map(map_to_array) |
|
|
|
def map_to_pred(batch): |
|
features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt") |
|
input_values = features.input_values.to(device) |
|
attention_mask = features.attention_mask.to(device) |
|
with torch.no_grad(): |
|
logits = model(input_values, attention_mask=attention_mask).logits |
|
pred_ids = torch.argmax(logits, dim=-1) |
|
batch["predicted"] = processor.batch_decode(pred_ids) |
|
batch["target"] = batch["sentence"] |
|
return batch |
|
|
|
result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys())) |
|
|
|
wer = load_metric("wer") |
|
|
|
print(wer.compute(predictions=result["predicted"], references=result["target"])) |
|
``` |
|
|
|
`CER: 0.842832469775475` |
|
|
|
Inference with GPT LM: |
|
```python |
|
import torchaudio |
|
from datasets import load_dataset, load_metric |
|
from transformers import ( |
|
Wav2Vec2ForCTC, |
|
Wav2Vec2Processor, |
|
) |
|
import torch |
|
import re |
|
from transformers import AutoTokenizer, AutoModelWithLMHead |
|
|
|
model_name = "voidful/wav2vec2-large-xlsr-53-tw" |
|
device = "cuda" |
|
processor_name = "voidful/wav2vec2-large-xlsr-53-tw" |
|
|
|
chars_to_ignore_regex = r"[¥•＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､ 、〃〈〉《》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏﹑﹔·'℃°•·．﹑︰〈〉─《﹖﹣﹂﹁﹔！？｡。＂＃＄％＆＇（）＊＋，﹐－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏.．!\"#$%&()*+,\-.\:;<=>?@\[\]\\\/^_`{|}~]" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ckiplab/gpt2-base-chinese") |
|
gpt_model = AutoModelWithLMHead.from_pretrained("ckiplab/gpt2-base-chinese").to(device) |
|
model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device) |
|
processor = Wav2Vec2Processor.from_pretrained(processor_name) |
|
|
|
ds = load_dataset("common_voice", 'zh-TW', data_dir="./cv-corpus-6.1-2020-12-11", split="test") |
|
|
|
resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000) |
|
|
|
def map_to_array(batch): |
|
speech, _ = torchaudio.load(batch["path"]) |
|
batch["speech"] = resampler.forward(speech.squeeze(0)).numpy() |
|
batch["sampling_rate"] = resampler.new_freq |
|
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'") |
|
return batch |
|
|
|
ds = ds.map(map_to_array) |
|
|
|
def map_to_pred(batch): |
|
features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt") |
|
input_values = features.input_values.to(device) |
|
attention_mask = features.attention_mask.to(device) |
|
with torch.no_grad(): |
|
logits = model(input_values, attention_mask=attention_mask).logits |
|
|
|
decoded_results = [] |
|
for logit in logits: |
|
pred_ids = torch.argmax(logit, dim=-1) |
|
mask = pred_ids.ge(1).unsqueeze(-1).expand(logit.size()) |
|
vocab_size = logit.size()[-1] |
|
voice_prob = torch.nn.functional.softmax((torch.masked_select(logit, mask).view(-1,vocab_size)),dim=-1) |
|
gpt_input = torch.cat((torch.tensor([tokenizer.cls_token_id]).to(device),pred_ids[pred_ids>0]), 0) |
|
gpt_prob = torch.nn.functional.softmax(gpt_model(gpt_input).logits, dim=-1)[:voice_prob.size()[0],:] |
|
comb_pred_ids = torch.argmax(gpt_prob*voice_prob, dim=-1) |
|
decoded_results.append(processor.decode(comb_pred_ids)) |
|
|
|
batch["predicted"] = decoded_results |
|
batch["target"] = batch["sentence"] |
|
return batch |
|
|
|
|
|
result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys())) |
|
|
|
wer = load_metric("wer") |
|
|
|
print(wer.compute(predictions=result["predicted"], references=result["target"])) |
|
``` |
|
|
|
`CER 0.7803108808290156` |
