Downloads · 30 days
3
1% of all-time downloads
group-dro_xlsr_set_2
bartelds/group-dro_xlsr_set_2
group-dro_xlsr_set_2 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 Group-DRO XLSR-based automatic speech recognition (ASR) model trained with ESPnet. The model was trained on balanced training data from set 2.
All-time downloads
202
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
- 17fc508f
Model card
From the Hugging Face model README
Group-DRO XLSR-based ASR model - set 2
This repository contains a Group-DRO XLSR-based automatic speech recognition (ASR) model trained with ESPnet.
The model was trained on balanced training data from set 2.
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 = "group-dro_xlsr_set_2/config.yaml"
asr_model_file = "group-dro_xlsr_set_2/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