MMLForge Search models, datasets, tasks… Start free
Home › Models › Automatic Speech Recognition › arijitx/wav2vec2-large-xlsr-bengali
W

arijitx/wav2vec2-large-xlsr-bengali

Automatic Speech Recognition·arijitx· 2.2K· 6
transformers cc-by-sa-4.0 Automatic Speech Recognition dataset:OpenSLRlicense:cc-by-sa-4.0

Wav2Vec2-Large-XLSR-Bengali Fine-tuned facebook/wav2vec2-large-xlsr-53 Bengali using a subset of 40,000 utterances from Bengali ASR training data set containing ~196K utterances. Tested WER using ~4200 held out from training. When using this model, make sure that your speech input is sampled at 16kHz. Train Script can be Found at : train.py

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull arijitx/wav2vec2-large-xlsr-bengali

Model details

Task
Automatic Speech Recognition
Provider
arijitx
Framework
transformers
Size
3.5 GB
License
cc-by-sa-4.0
Downloads
2.2K
Likes
6
Updated
2021-09-23

About arijitx/wav2vec2-large-xlsr-bengali

Wav2Vec2-Large-XLSR-Bengali Fine-tuned facebook/wav2vec2-large-xlsr-53 Bengali using a subset of 40,000 utterances from Bengali ASR training data set containing ~196K utterances. Tested WER using ~4200 held out from training. When using this model, make sure that your speech input is sampled at 16kHz. Train Script can be Found at : train.py

Related Automatic Speech Recognition

S pyannote/speaker-diarization-3.1 Automatic Speech Recognition 8.2M 2.5K 🤗 HF W argmaxinc/whisperkit-coreml Automatic Speech Recognition 8.1M 193 🤗 HF W openai/whisper-large-v3-turbo Automatic Speech Recognition ·808.9M params 7.1M 3.1K 🤗 HF W openai/whisper-base Automatic Speech Recognition ·72.6M params 6.2M 274 🤗 HF W jonatasgrosman/wav2vec2-large-xlsr-53-japanese Automatic Speech Recognition 6.1M 61 🤗 HF W openai/whisper-large-v3 Automatic Speech Recognition ·1.5B params 5.7M 5.9K 🤗 HF

Browse all Automatic Speech Recognition models →