Downloads · 30 days
12
3% of all-time downloads
Quyashbek/wav2vec2-xls-r-300m-karakalpak
wav2vec2-xls-r-300m-karakalpak is a automatic speech recognition model from Quyashbek. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m for Automatic Speech Recognition (ASR) in the Karakalpak language.
Downloads · 30 days
12
3% of all-time downloads
All-time downloads
404
Public
Parameters
315M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m for Automatic Speech Recognition (ASR) in the Karakalpak language.
Quyashbek Allanazarov
Evaluation was performed on a held-out test set.
| Metric | Score |
|---|---|
| WER (Word Error Rate) | 21.21% |
| CER (Character Error Rate) | 4.34% |
facebook/wav2vec2-xls-r-300mimport torch
import librosa
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
model_id = "Quyashbek/wav2vec2-xls-r-300m-karakalpak-asr"
processor = Wav2Vec2Processor.from_pretrained(model_id)
model = Wav2Vec2ForCTC.from_pretrained(model_id)
speech, sr = librosa.load("your_audio.wav", sr=16000)
inputs = processor(speech, sampling_rate=16000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values).logits
pred_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(pred_ids)[0]
print(transcription)