Downloads · 30 days
137
1% of all-time downloads
carlosdanielhernandezmena/wav2vec2-large-xlsr-53-spanish-ep5-944h
wav2vec2-large-xlsr-53-spanish-ep5-944h is a automatic speech recognition model from carlosdanielhernandezmena. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-4.0.
Paper: The state of end-to-end systems for Mexican Spanish speech recognition
Downloads · 30 days
137
1% of all-time downloads
All-time downloads
24K
Public
Parameters
315M
2.5 GB on disk
Likes
5
Public
Click a slice to open those files.
.bin1.3 GB · 50%
From the Hugging Face model README
Paper: The state of end-to-end systems for Mexican Spanish speech recognition
The "wav2vec2-large-xlsr-53-spanish-ep5-944h" is an acoustic model suitable for Automatic Speech Recognition in Spanish. It is the result of fine-tuning the model "facebook/wav2vec2-large-xlsr-53" for 5 epochs with around 944 hours of Spanish data gathered or developed by the CIEMPIESS-UNAM Project since 2012. Most of the data is available at the the CIEMPIESS-UNAM Project homepage http://www.ciempiess.org/. The rest can be found in public repositories such as LDC or OpenSLR
The specific list of corpora used to fine-tune the model is:
The fine-tuning process was performed during November (2022) in the servers of the Language and Voice Lab (https://lvl.ru.is/) at Reykjavík University (Iceland) by Carlos Daniel Hernández Mena.
import torch
from transformers import Wav2Vec2Processor
from transformers import Wav2Vec2ForCTC
#Load the processor and model.
MODEL_NAME="carlosdanielhernandezmena/wav2vec2-large-xlsr-53-spanish-ep5-944h"
processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_NAME)
#Load the dataset
from datasets import load_dataset, load_metric, Audio
ds=load_dataset("ciempiess/ciempiess_test", split="test")
#Downsample to 16kHz
ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
#Process the dataset
def prepare_dataset(batch):
audio = batch["audio"]
#Batched output is "un-batched" to ensure mapping is correct
batch["input_values"] = processor(audio["array"], sampling_rate=audio["sampling_rate"]).input_values[0]
with processor.as_target_processor():
batch["labels"] = processor(batch["normalized_text"]).input_ids
return batch
ds = ds.map(prepare_dataset, remove_columns=ds.column_names,num_proc=1)
#Define the evaluation metric
import numpy as np
wer_metric = load_metric("wer")
def compute_metrics(pred):
pred_logits = pred.predictions
pred_ids = np.argmax(pred_logits, axis=-1)
pred.label_ids[pred.label_ids == -100] = processor.tokenizer.pad_token_id
pred_str = processor.batch_decode(pred_ids)
#We do not want to group tokens when computing the metrics
label_str = processor.batch_decode(pred.label_ids, group_tokens=False)
wer = wer_metric.compute(predictions=pred_str, references=label_str)
return {"wer": wer}
#Do the evaluation (with batch_size=1)
model = model.to(torch.device("cuda"))
def map_to_result(batch):
with torch.no_grad():
input_values = torch.tensor(batch["input_values"], device="cuda").unsqueeze(0)
logits = model(input_values).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_str"] = processor.batch_decode(pred_ids)[0]
batch["sentence"] = processor.decode(batch["labels"], group_tokens=False)
return batch
results = ds.map(map_to_result,remove_columns=ds.column_names)
#Compute the overall WER now.
print("Test WER: {:.3f}".format(wer_metric.compute(predictions=results["pred_str"], references=results["sentence"])))
Test Result: 0.112
When publishing results based on these models please refer to:
@misc{mena2022xlrs53spanish,
title={Acoustic Model in Spanish: wav2vec2-large-xlsr-53-spanish-ep5-944h.},
author={Hernandez Mena, Carlos Daniel},
url={https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-spanish-ep5-944h},
year={2022}
}
The author wants to thank to the social service program "Desarrollo de Tecnologías del Habla" at the Facultad de Ingeniería (FI) of the Universidad Nacional Autónoma de México (UNAM). He also thanks to the social service students for all the hard work.
Special thanks to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make this model possible. The author also thanks to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture.