Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Swahili
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 Akashpb13/Swahili_xlsr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Akashpb13/Swahili_xlsr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Akashpb13/Swahili_xlsr")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Akashpb13/Swahili_xlsr") model = AutoModelForCTC.from_pretrained("Akashpb13/Swahili_xlsr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Cloning model Error
#1
by mkapa - opened
Sorry i tried to run command "python eval.py --model_id Akashpb13/Swahili_xlsr --dataset mozilla-foundation/common_voice_8_0 --config sw --split test"
and got the error below;
local_extracted_archive = dl_manager.extract(archive_path) if not dl_manager.is_streaming else None
AttributeError: 'DownloadManager' object has no attribute 'is_streaming'
some help please