Robust Speech Recognition Event
Collection
The event ran from January 24 to February 7, 2022. Participants used the wav2vec2 model series to develop cutting-edge speech recognition models.
•
13 items
•
Updated
•
1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
mozilla-foundation/common_voice_8_0
with split test
python eval.py --model_id kingabzpro/wav2vec2-large-xls-r-300m-Urdu --dataset mozilla-foundation/common_voice_8_0 --config ur --split test
from datasets import load_dataset, Audio
from transformers import pipeline
model = "kingabzpro/wav2vec2-large-xls-r-300m-Urdu"
data = load_dataset("mozilla-foundation/common_voice_8_0",
"ur",
split="test",
streaming=True,
use_auth_token=True)
sample_iter = iter(data.cast_column("path",
Audio(sampling_rate=16_000)))
sample = next(sample_iter)
asr = pipeline("automatic-speech-recognition", model=model)
prediction = asr(sample["path"]["array"],
chunk_length_s=5,
stride_length_s=1)
prediction
# => {'text': 'اب یہ ونگین لمحاتانکھار دلمیں میںفوث کریلیا اجائ'}
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
---|---|---|---|---|---|
3.6398 | 30.77 | 400 | 3.3517 | 1.0 | 1.0 |
2.9225 | 61.54 | 800 | 2.5123 | 1.0 | 0.8310 |
1.2568 | 92.31 | 1200 | 0.9699 | 0.6273 | 0.2575 |
0.8974 | 123.08 | 1600 | 0.9715 | 0.5888 | 0.2457 |
0.7151 | 153.85 | 2000 | 0.9984 | 0.5588 | 0.2353 |
0.6416 | 184.62 | 2400 | 0.9889 | 0.5607 | 0.2370 |
Without LM | With LM (run ./eval.py ) |
---|---|
52.03 | 39.89 |
Base model
facebook/wav2vec2-xls-r-300m