README.md

metadata

language: de
datasets:
  - common_voice
metrics:
  - wer
  - cer
tags:
  - audio
  - automatic-speech-recognition
  - speech
  - xlsr-fine-tuning-week
license: apache-2.0
model-index:
  - name: XLSR Wav2Vec2 German by Jonatas Grosman
    results:
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice de
          type: common_voice
          args: de
        metrics:
          - name: Test WER
            type: wer
            value: 10.55
          - name: Test CER
            type: cer
            value: 2.81

Wav2Vec2-Large-XLSR-53-German

Fine-tuned facebook/wav2vec2-large-xlsr-53 on German using the Common Voice. When using this model, make sure that your speech input is sampled at 16kHz.

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:

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

The model can be evaluated as follows on the German test data of Common Voice.

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

LANG_ID = "de"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-german"
DEVICE = "cuda"

CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]

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

wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py

chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"

processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
model.to(DEVICE)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
    return batch

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(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).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)

predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]

print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")

Test Result:

In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-06-17). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.

Model	WER	CER
jonatasgrosman/wav2vec2-large-xlsr-53-german	10.55%	2.81%
Noricum/wav2vec2-large-xlsr-53-german	11.06%	2.99%
maxidl/wav2vec2-large-xlsr-german	13.10%	3.64%
marcel/wav2vec2-large-xlsr-53-german	15.97%	4.37%
flozi00/wav2vec-xlsr-german	16.13%	4.33%
facebook/wav2vec2-large-xlsr-53-german	17.15%	5.79%
MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-German	19.31%	5.41%