Downloads · 30 days
0
wav2vec2-base-ASR-telugu
henilp105/wav2vec2-base-ASR-telugu
wav2vec2-base-ASR-telugu is a automatic speech recognition model from henilp105. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Telugu using the ASR IIIT-H dataset. When using this model, make sure that your speech input is sampled at 16kHz.
Access
Public
Updated Nov 2, 2022
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Access
- Public
- Created
- Oct 29, 2022
- Updated
- Nov 2, 2022
- SHA
- 008e3e00
Model card
From the Hugging Face model README
Wav2Vec2-Large-XLSR-53-Telugu
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Telugu using the ASR IIIT-H dataset. When using this model, make sure that your speech input is sampled at 16kHz.
Test Result: 41.90%
Training
70% of the O part of ASR IIIT-H Telugu dataset was used for training.
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Languages
- te
- Created
- Oct 29, 2022
- Updated
- Nov 2, 2022