Downloads · 30 days
4
3% of all-time downloads
ctc-baseline_xlsr_set_2-extra
bartelds/ctc-baseline_xlsr_set_2-extra
ctc-baseline_xlsr_set_2-extra is a machine learning model from bartelds. 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 cc-by-nc-4.0.
This repository contains a CTC-Baseline XLSR-based automatic speech recognition (ASR) model trained with ESPnet. The model was trained on unbalanced training data from set 2-extra.
All-time downloads
157
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth1.3 GB · 100%
At a glance
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Mar 3, 2025
- Updated
- Mar 3, 2025
- SHA
- 7db9ab5a
Model card
From the Hugging Face model README
CTC-DRO XLSR-based ASR model - set 2-extra
This repository contains a CTC-Baseline XLSR-based automatic speech recognition (ASR) model trained with ESPnet.
The model was trained on unbalanced training data from set 2-extra.
Intended Use
This model is intended for ASR. Users can run inference using the provided checkpoint (valid.loss.best.pth) and configuration file (config.yaml):
import soundfile as sf
from espnet2.bin.asr_inference import Speech2Text
asr_train_config = "ctc-baseline_xlsr_set_2-extra/config.yaml"
asr_model_file = "ctc-baseline_xlsr_set_2-extra/valid.loss.best.pth"
model = Speech2Text.from_pretrained(
asr_train_config=asr_train_config,
asr_model_file=asr_model_file
)
speech, _ = sf.read("input.wav")
text, *_ = model(speech)[0]
print("Recognized text:", text)
How to Use
- Clone this repository.
- Use ESPnet’s inference scripts with the provided
config.yamland checkpoint file. - Ensure any external resources referenced in
config.yamlare available at the indicated relative paths.
- License
- cc-by-nc-4.0
- Languages
- multilingual
- Created
- Mar 3, 2025
- Updated
- Mar 3, 2025