Fine-tuned XLSR-53 large model for speech recognition in German
Fine-tuned facebook/wav2vec2-large-xlsr-53 on German using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz.
This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :)
The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
Usage
The model can be used directly (without a language model) as follows...
Using the HuggingSound library:
from huggingsound import SpeechRecognitionModel
model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-german")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
transcriptions = model.transcribe(audio_paths)
Writing your own inference script:
import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "de"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-german"
SAMPLES = 10
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
batch["sentence"] = batch["sentence"].upper()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], 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)
predicted_sentences = processor.batch_decode(predicted_ids)
for i, predicted_sentence in enumerate(predicted_sentences):
print("-" * 100)
print("Reference:", test_dataset[i]["sentence"])
print("Prediction:", predicted_sentence)
Reference | Prediction |
---|---|
ZIEHT EUCH BITTE DRAUSSEN DIE SCHUHE AUS. | ZIEHT EUCH BITTE DRAUSSEN DIE SCHUHE AUS |
ES KOMMT ZUM SHOWDOWN IN GSTAAD. | ES KOMMT ZUG STUNDEDAUTENESTERKT |
IHRE FOTOSTRECKEN ERSCHIENEN IN MODEMAGAZINEN WIE DER VOGUE, HARPER’S BAZAAR UND MARIE CLAIRE. | IHRE FOTELSTRECKEN ERSCHIENEN MIT MODEMAGAZINEN WIE DER VALG AT DAS BASIN MA RIQUAIR |
FELIPE HAT EINE AUCH FÜR MONARCHEN UNGEWÖHNLICH LANGE TITELLISTE. | FELIPPE HAT EINE AUCH FÜR MONACHEN UNGEWÖHNLICH LANGE TITELLISTE |
ER WURDE ZU EHREN DES REICHSKANZLERS OTTO VON BISMARCK ERRICHTET. | ER WURDE ZU EHREN DES REICHSKANZLERS OTTO VON BISMARCK ERRICHTET M |
WAS SOLLS, ICH BIN BEREIT. | WAS SOLL'S ICH BIN BEREIT |
DAS INTERNET BESTEHT AUS VIELEN COMPUTERN, DIE MITEINANDER VERBUNDEN SIND. | DAS INTERNET BESTEHT AUS VIELEN COMPUTERN DIE MITEINANDER VERBUNDEN SIND |
DER URANUS IST DER SIEBENTE PLANET IN UNSEREM SONNENSYSTEM. | DER URANUS IST DER SIEBENTE PLANET IN UNSEREM SONNENSYSTEM |
DIE WAGEN ERHIELTEN EIN EINHEITLICHES ERSCHEINUNGSBILD IN WEISS MIT ROTEM FENSTERBAND. | DIE WAGEN ERHIELTEN EIN EINHEITLICHES ERSCHEINUNGSBILD IN WEISS MIT ROTEM FENSTERBAND |
SIE WAR DIE COUSINE VON CARL MARIA VON WEBER. | SIE WAR DIE COUSINE VON KARL-MARIA VON WEBER |
Evaluation
- To evaluate on
mozilla-foundation/common_voice_6_0
with splittest
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-german --dataset mozilla-foundation/common_voice_6_0 --config de --split test
- To evaluate on
speech-recognition-community-v2/dev_data
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-german --dataset speech-recognition-community-v2/dev_data --config de --split validation --chunk_length_s 5.0 --stride_length_s 1.0
Citation
If you want to cite this model you can use this:
@misc{grosman2021xlsr53-large-german,
title={Fine-tuned {XLSR}-53 large model for speech recognition in {G}erman},
author={Grosman, Jonatas},
howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-german}},
year={2021}
}
- Downloads last month
- 1,321
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Datasets used to train jonatasgrosman/wav2vec2-large-xlsr-53-german
Spaces using jonatasgrosman/wav2vec2-large-xlsr-53-german 9
Evaluation results
- Test WER on Common Voice deself-reported12.060
- Test CER on Common Voice deself-reported2.920
- Test WER (+LM) on Common Voice deself-reported8.740
- Test CER (+LM) on Common Voice deself-reported2.280
- Dev WER on Robust Speech Event - Dev Dataself-reported32.750
- Dev CER on Robust Speech Event - Dev Dataself-reported13.640
- Dev WER (+LM) on Robust Speech Event - Dev Dataself-reported26.600
- Dev CER (+LM) on Robust Speech Event - Dev Dataself-reported12.580