Automatic Speech Recognition
Transformers
Safetensors
Finnish
wav2vec2
finnish
Eval Results (legacy)
Instructions to use GetmanY1/wav2vec2-base-fi-voxpopuli-v2-100h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GetmanY1/wav2vec2-base-fi-voxpopuli-v2-100h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="GetmanY1/wav2vec2-base-fi-voxpopuli-v2-100h")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("GetmanY1/wav2vec2-base-fi-voxpopuli-v2-100h") model = AutoModelForCTC.from_pretrained("GetmanY1/wav2vec2-base-fi-voxpopuli-v2-100h", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token": { | |
| "content": "<s>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "</s>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<pad>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| } | |
| } | |