Wav2Vec2-Large-XLSR-53-Spanish

使用 Common Voice 对西班牙语进行了精调 facebook/wav2vec2-large-xlsr-53 。在使用此模型时，请确保您的语音输入的采样频率为16kHz。

用法

可以直接使用该模型（无需使用语言模型），如下所示：

import torch

import torchaudio

from datasets import load_dataset

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

test_dataset = load_dataset("common_voice", "es", split="test[:2%]").

processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-spanish")

model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-spanish")

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])

评估

可以按以下方法在Common Voice的乌克兰测试数据上评估模型。

import torch

import torchaudio

from datasets import load_dataset, load_metric

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

import re

test_dataset = load_dataset("common_voice", "es", split="test")

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-spanish")

model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-spanish")

model.to("cuda")

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'

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=8)

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

测试结果： %

训练

训练时使用了Common Voice的训练集和验证集。

用于训练的脚本可以在 ??? 中找到。