Downloads · 30 days
16
14% of all-time downloads
xlsr-1b-aft-mid-kcn
vitthalbhandari/xlsr-1b-aft-mid-kcn
xlsr-1b-aft-mid-kcn is a automatic speech recognition model from vitthalbhandari. Use it when you need speech turned into text. The card lists the license as cc-by-nc-4.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the Mozilla Common Voice Spontaneous Speech dataset for Nubi (kcn).
All-time downloads
112
Public
Parameters
994M
8.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- cc-by-nc-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 7, 2026
- Updated
- Mar 15, 2026
- SHA
- c83d51a4
Model card
From the Hugging Face model README
XLS-R 1B Adapter Fine-tuned for Nubi
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the Mozilla Common Voice Spontaneous Speech dataset for Nubi (kcn).
Training
- Base model: facebook/wav2vec2-xls-r-1b
- Fine-tuning method: Attention adapter layers (adapter_attn_dim=256)
- Dataset: Mozilla Common Voice Spontaneous Speech
Usage
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
processor = Wav2Vec2Processor.from_pretrained("vitthalbhandari/xlsr-1b-aft-mid-kcn")
model = Wav2Vec2ForCTC.from_pretrained("vitthalbhandari/xlsr-1b-aft-mid-kcn")
# Transcribe audio
inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
- Task
- Automatic Speech Recognition
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Languages
- kcn
- Created
- Mar 7, 2026
- Updated
- Mar 15, 2026