Downloads · 30 days
12
9% of all-time downloads
nadi2025_task3_B1
herwoww/nadi2025_task3_B1
nadi2025_task3_B1 is a automatic speech recognition model from herwoww. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.
All-time downloads
139
Public
Parameters
155M
620 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors619 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- cc-by-4.0
- Model type
- speecht5
- Access
- Public
- Created
- May 28, 2025
- Updated
- May 28, 2025
- SHA
- b10e8bcd
Base models
Model card
From the Hugging Face model README
import librosa
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
model_id="herwoww/nadi2025_task3_B1"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
wav, sr = librosa.load("audio.wav", sr=16000)
pipe(wav, generate_kwargs={'num_beams': 10, 'early_stopping': True})['text']
- Task
- Automatic Speech Recognition
- Type
- speecht5
- License
- cc-by-4.0
- Languages
- ar
- Created
- May 28, 2025
- Updated
- May 28, 2025