Fonxlsr

🚀 Wav2Vec2-Large-XLSR-53-Fon

本項目基於 Fon (or Fongbe) 數據集，對 facebook/wav2vec2-large-xlsr-53 模型進行微調，得到適用於 Fon 語言的語音識別模型。使用該模型時，請確保語音輸入的採樣率為 16kHz。

📦 模型信息

🚀 快速開始

模型使用

本模型可以直接使用（無需語言模型），示例代碼如下：

import json
import random
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor


#Load test_dataset from saved files in folder
from datasets import load_dataset, load_metric

#for test
for root, dirs, files in os.walk(test/):
  test_dataset= load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")

#Remove unnecessary chars
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\“\\%\\‘\\”]'
def remove_special_characters(batch):
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
    return batch

test_dataset = test_dataset.map(remove_special_characters)

processor = Wav2Vec2Processor.from_pretrained("chrisjay/wav2vec2-large-xlsr-53-fon") 
model = Wav2Vec2ForCTC.from_pretrained("chrisjay/wav2vec2-large-xlsr-53-fon") 

#No need for resampling because audio dataset already at 16kHz
#resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
  speech_array, sampling_rate = torchaudio.load(batch["path"])
  batch["speech"]=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():
  tlogits = 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])

模型評估

可以使用以下代碼在 Fon 測試集上對模型進行評估：

import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re

for root, dirs, files in os.walk(test/):
  test_dataset = load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")

chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\“\\%\\‘\\”]'
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
    return batch

test_dataset = test_dataset.map(remove_special_characters)
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("chrisjay/wav2vec2-large-xlsr-53-fon")
model = Wav2Vec2ForCTC.from_pretrained("chrisjay/wav2vec2-large-xlsr-53-fon")
model.to("cuda")

# 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"] = speech_array[0].numpy()
    batch["sampling_rate"] = sampling_rate
    batch["target_text"] = batch["sentence"]
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

#Evaluation on test dataset
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=8)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))

測試結果：14.97 %

模型訓練

Fon 數據集 被劃分為 訓練集（8235 個樣本）、驗證集（1107 個樣本）和 測試集（1061 個樣本）。訓練腳本可以在 這裡 找到。

👥 項目貢獻者

• Chris C. Emezue (Twitter)|(chris.emezue@gmail.com)
• Bonaventure F.P. Dossou (HuggingFace 用戶名: bonadossou)|(Twitter)|(femipancrace.dossou@gmail.com)

📖 相關研究

本項目是 OkwuGbé: End-to-End Speech Recognition for Fon and Igbo 研究的延續。