Downloads · 30 days
0
jsalt26-csr-lab
Borrison/jsalt26-csr-lab
jsalt26-csr-lab is a machine learning model from Borrison. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Pre-trained weights for the JSALT 2026 Continuous Speech Recognition lab.
Access
Public
Updated Jun 19, 2026
Repo size
3.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt3.4 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- 9ce720a8
Model card
From the Hugging Face model README
JSALT 2026 — CSR Lab: Pre-trained Character ASR Model
Pre-trained weights for the JSALT 2026 Continuous Speech Recognition lab.
Model
- Encoder:
facebook/hubert-base-ls960(HuBERT-base, frozen for first 1000 steps) - Output head: linear 768 → 33 (character-level vocabulary)
- Loss: CTC with blank token at index 0
- Tokenizer:
CharacterTokenizer(33-class:<blk>,<pad>,<unk>,<bos>,<eos>, A–Z, space, apostrophe) - Training data: LibriSpeech
train-clean-5(~5.4 h)
Files
| File | Description |
|---|---|
speech_encoder_char.pt | model.state_dict() — load directly with model.load_state_dict(...) |
Usage
from huggingface_hub import hf_hub_download
import torch
weights_path = hf_hub_download(repo_id="Borrison/jsalt26-csr-lab",
filename="speech_encoder_char.pt")
state_dict = torch.load(weights_path, map_location=device)
model.load_state_dict(state_dict)
- License
- mit
- Languages
- en
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026