YAML Metadata
Error:
Invalid YAML in README.md: can not read a block mapping entry; a multiline key may not be an implicit key (6:8)
3 | - common_voice #TODO: remove if you did ...
4 | - TODO: add more datasets if you have u ...
5 | dataset name as the one found [here](ht ...
6 | metrics:
------------^
7 | - wer
8 | - cer
(You can use a tool like http://www.yamllint.com/ to check it)
Wav2Vec2-Large-XLSR-53-Japanese
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice, ... and ... dataset{s}. 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:
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "ja", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("qqhann/w2v_hf_commonvoice_from_xlsr53_pretrain_0329UTC1500")
model = Wav2Vec2ForCTC.from_pretrained("qqhann/w2v_hf_commonvoice_from_xlsr53_pretrain_0329UTC1500")
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 Japanese test data of Common Voice.
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
test_dataset = load_dataset("common_voice", "ja", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("qqhann/w2v_hf_commonvoice_from_xlsr53_pretrain_0329UTC1500")
model = Wav2Vec2ForCTC.from_pretrained("qqhann/w2v_hf_commonvoice_from_xlsr53_pretrain_0329UTC1500")
model.to("cuda")
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]' # TODO: adapt this list to include all special characters you removed from the data
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"])))
Test Result: 70.18 %
Training
The Common Voice train, validation, and ... datasets were used for training as well as ... and ...
The script used for training can be found here
- Downloads last month
- 2