138 lines
4.0 KiB
Markdown
138 lines
4.0 KiB
Markdown
---
|
||
language:
|
||
- yue
|
||
language_bcp47:
|
||
- zh-HK
|
||
datasets:
|
||
- common_voice
|
||
metrics:
|
||
- cer
|
||
|
||
tags:
|
||
- audio
|
||
- automatic-speech-recognition
|
||
- speech
|
||
- xlsr-fine-tuning-week
|
||
license: apache-2.0
|
||
model-index:
|
||
- name: wav2vec2-large-xlsr-cantonese
|
||
results:
|
||
- task:
|
||
name: Speech Recognition
|
||
type: automatic-speech-recognition
|
||
dataset:
|
||
name: Common Voice zh-HK
|
||
type: common_voice
|
||
args: zh-HK
|
||
metrics:
|
||
- name: Test CER
|
||
type: cer
|
||
value: 15.36
|
||
---
|
||
|
||
# Wav2Vec2-Large-XLSR-53-Cantonese
|
||
|
||
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Cantonese using the [Common Voice](https://huggingface.co/datasets/common_voice).
|
||
When using this model, make sure that your speech input is sampled at 16kHz.
|
||
|
||
## Usage
|
||
|
||
The model can be used directly (without a language model) as follows:
|
||
|
||
```python
|
||
import torch
|
||
import torchaudio
|
||
from datasets import load_dataset
|
||
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
||
|
||
test_dataset = load_dataset("common_voice", "zh-HK", split="test[:2%]")
|
||
|
||
processor = Wav2Vec2Processor.from_pretrained("ctl/wav2vec2-large-xlsr-cantonese")
|
||
model = Wav2Vec2ForCTC.from_pretrained("ctl/wav2vec2-large-xlsr-cantonese")
|
||
|
||
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
||
|
||
# Preprocessing the datasets.
|
||
# We need to read the aduio files as arrays
|
||
def speech_file_to_array_fn(batch):
|
||
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
||
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
||
return batch
|
||
|
||
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
||
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
||
|
||
with torch.no_grad():
|
||
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
||
|
||
predicted_ids = torch.argmax(logits, dim=-1)
|
||
|
||
print("Prediction:", processor.batch_decode(predicted_ids))
|
||
print("Reference:", test_dataset["sentence"][:2])
|
||
```
|
||
|
||
|
||
## Evaluation
|
||
|
||
The model can be evaluated as follows on the Chinese (Hong Kong) test data of Common Voice.
|
||
|
||
|
||
```python
|
||
!pip install jiwer
|
||
import torch
|
||
import torchaudio
|
||
from datasets import load_dataset, load_metric
|
||
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
||
import re
|
||
import argparse
|
||
|
||
lang_id = "zh-HK"
|
||
model_id = "ctl/wav2vec2-large-xlsr-cantonese"
|
||
|
||
chars_to_ignore_regex = '[\,\?\.\!\-\;\:"\“\%\‘\”\<5C>\．\⋯\！\－\：\–\。\》\,\）\,\？\；\～\~\…\︰\，\（\」\‧\《\﹔\、\—\／\,\「\﹖\·\']'
|
||
|
||
test_dataset = load_dataset("common_voice", f"{lang_id}", split="test")
|
||
cer = load_metric("cer")
|
||
|
||
processor = Wav2Vec2Processor.from_pretrained(f"{model_id}")
|
||
model = Wav2Vec2ForCTC.from_pretrained(f"{model_id}")
|
||
model.to("cuda")
|
||
|
||
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
||
|
||
# Preprocessing the datasets.
|
||
# We need to read the aduio files as arrays
|
||
def speech_file_to_array_fn(batch):
|
||
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
||
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
||
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
||
return batch
|
||
|
||
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
||
|
||
# Preprocessing the datasets.
|
||
# We need to read the aduio files as arrays
|
||
def evaluate(batch):
|
||
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
||
with torch.no_grad():
|
||
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).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=16)
|
||
|
||
print("CER: {:2f}".format(100 * cer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
||
```
|
||
|
||
|
||
**Test Result**: 15.51 %
|
||
|
||
|
||
## Training
|
||
|
||
The Common Voice `train`, `validation` were used for training.
|
||
|
||
The script used for training will be posted [here](https://github.com/chutaklee/CantoASR)
|