Wav2vec2 Large Xlsr 53 Breton

🚀 wav2vec2-large-xlsr-53-breton

該模型是用於布列塔尼語的語音識別模型，可直接使用進行語音識別任務，無需額外的語言模型。

🚀 快速開始

該模型可以直接使用（無需語言模型），如下所示：

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

lang = "br"
test_dataset = load_dataset("common_voice", lang, split="test[:2%]") 

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

resampler = torchaudio.transforms.Resample(48_000, 16_000)

chars_to_ignore_regex = '[\\,\,\?\.\!\;\:\"\“\%\”\�\(\)\/\«\»\½\…]'

# 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"] = resampler(speech_array).squeeze().numpy()
   batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
   batch["sentence"] = re.sub("ʼ", "'", batch["sentence"])
   batch["sentence"] = re.sub("’", "'", batch["sentence"])
   batch["sentence"] = re.sub('‘', "'", batch["sentence"])
   return batch

nb_samples = 2
test_dataset = test_dataset.map(speech_file_to_array_fn)

inputs = processor(test_dataset["speech"][:nb_samples], 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"][:nb_samples])

上述代碼對前兩個樣本的預測結果如下：

• 預測結果: ["neller ket dont a-benn eus netra la vez ser merc'hed evel sich", 'an eil hag egile']
• 參考結果: ["N'haller ket dont a-benn eus netra pa vezer nec'het evel-se.", 'An eil hag egile.']

該模型可以在Common Voice的布列塔尼語測試數據上進行評估，如下所示：

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

lang = 'br'
test_dataset = load_dataset("common_voice", lang, split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained('Marxav/wav2vec2-large-xlsr-53-breton')
model = Wav2Vec2ForCTC.from_pretrained('Marxav/wav2vec2-large-xlsr-53-breton')
model.to("cuda")

chars_to_ignore_regex = '[\\,\,\?\.\!\;\:\"\“\%\”\�\(\)\/\«\»\½\…]'

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()
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
  batch["sentence"] = re.sub("ʼ", "'", batch["sentence"])
  batch["sentence"] = re.sub("’", "'", batch["sentence"])
  batch["sentence"] = re.sub('‘', "'", batch["sentence"])
  speech_array, sampling_rate = torchaudio.load(batch["path"])
  batch["speech"] = resampler(speech_array).squeeze().numpy()
  return batch

test_dataset = test_dataset.map(remove_special_characters)

test_dataset = test_dataset.map(speech_file_to_array_fn)

# Preprocessing the datasets.
# We need to read the audio 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=8)

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

測試結果：43.43%

📚 詳細文檔

🔧 技術細節

該模型名為“XLSR Wav2Vec2 Breton by Marxav”，用於語音識別任務。在Common Voice布列塔尼語數據集上進行測試，測試集的詞錯誤率（WER）為43.43%。

📄 許可證

本模型使用的許可證為Apache-2.0。