legacy-datasets/common_voice
Updated • 1.54k • 144
How to use Arxived/wav2vec2-large-xls-r-300m-ab-v4 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="Arxived/wav2vec2-large-xls-r-300m-ab-v4") # Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("Arxived/wav2vec2-large-xls-r-300m-ab-v4")
model = AutoModelForCTC.from_pretrained("Arxived/wav2vec2-large-xls-r-300m-ab-v4")YAML Metadata Error:"model-index[0].name" is not allowed to be empty
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.2793 | 27.27 | 300 | 3.0737 | 1.0 |
| 1.5348 | 54.55 | 600 | 0.6312 | 0.6334 |