Automatic Speech Recognition
Transformers
PyTorch
Oriya
wav2vec2
hf-asr-leaderboard
model_for_talk
mozilla-foundation/common_voice_7_0
robust-speech-event
Eval Results (legacy)
Instructions to use Harveenchadha/odia_large_wav2vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harveenchadha/odia_large_wav2vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Harveenchadha/odia_large_wav2vec2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Harveenchadha/odia_large_wav2vec2") model = AutoModelForCTC.from_pretrained("Harveenchadha/odia_large_wav2vec2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Harveenchadha/odia_large_wav2vec2: direct link, hf CLI and curl.
- Browser
- Download file 1.21 kB
-
https://huggingface.co/Harveenchadha/odia_large_wav2vec2/resolve/main/README.md
- Command line
-
hf download hf://Harveenchadha/odia_large_wav2vec2/README.md
-
curl -L -o README.md https://huggingface.co/Harveenchadha/odia_large_wav2vec2/resolve/main/README.md
1.21 kB
metadata
license: apache-2.0
language:
- or
tags:
- automatic-speech-recognition
- hf-asr-leaderboard
- model_for_talk
- mozilla-foundation/common_voice_7_0
- or
- robust-speech-event
datasets:
- Harveenchadha/indic-voice
model-index:
- name: Hindi Large
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice
type: common_voice
args: or
metrics:
- name: Test WER
type: wer
value: 54.26
- name: Test CER
type: cer
value: 11.36
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice-7.0
type: mozilla-foundation/common_voice_7_0
args: or
metrics:
- name: Test WER
type: wer
value: 53.58
- name: Test CER
type: cer
value: 11.26
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice-8.0
type: mozilla-foundation/common_voice_8_0
args: or
metrics:
- name: Test WER
type: wer
value: 55.26
- name: Test CER
type: cer
value: 13.01