Automatic Speech Recognition
Transformers
PyTorch
Slovenian
wav2vec2
Generated from Trainer
hf-asr-leaderboard
model_for_talk
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results (legacy)
Instructions to use DrishtiSharma/wav2vec2-large-xls-r-300m-sl-with-LM-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DrishtiSharma/wav2vec2-large-xls-r-300m-sl-with-LM-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="DrishtiSharma/wav2vec2-large-xls-r-300m-sl-with-LM-v2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("DrishtiSharma/wav2vec2-large-xls-r-300m-sl-with-LM-v2") model = AutoModelForCTC.from_pretrained("DrishtiSharma/wav2vec2-large-xls-r-300m-sl-with-LM-v2") - Notebooks
- Google Colab
- Kaggle
File size: 225 Bytes
736e004 | 1 2 3 4 5 6 7 8 9 | {
"epoch": 100.0,
"eval_loss": 0.28546908497810364,
"eval_runtime": 36.8636,
"eval_samples": 1193,
"eval_samples_per_second": 32.363,
"eval_steps_per_second": 1.031,
"eval_wer": 0.240081979212414
} |