Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use internalhell/wav2vec2-russian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use internalhell/wav2vec2-russian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="internalhell/wav2vec2-russian")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("internalhell/wav2vec2-russian") model = AutoModelForSpeechSeq2Seq.from_pretrained("internalhell/wav2vec2-russian", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 85151f50f34765dba593de302ceb8c0d8292300e37ea5a29765064ce636aae41
- Size of remote file:
- 1.26 GB
- SHA256:
- 29f6999838e3b1ea5905c7069d5f8aa0115c5390f26e8dc5673be1d76d222ca5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.