Automatic Speech Recognition
Transformers
PyTorch
Latin
wav2vec2
robust-speech-event
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use lsb/wav2vec2-base-it-latin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lsb/wav2vec2-base-it-latin with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lsb/wav2vec2-base-it-latin")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lsb/wav2vec2-base-it-latin") model = AutoModelForCTC.from_pretrained("lsb/wav2vec2-base-it-latin", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Librarian Bot: Add base_model information to model
#2
by librarian-bot - opened
README.md
CHANGED
|
@@ -9,6 +9,7 @@ datasets:
|
|
| 9 |
- lsb/poetaexmachina-mp3-recitations
|
| 10 |
metrics:
|
| 11 |
- wer
|
|
|
|
| 12 |
model-index:
|
| 13 |
- name: wav2vec2-base-it-latin
|
| 14 |
results:
|
|
@@ -16,8 +17,8 @@ model-index:
|
|
| 16 |
type: automatic-speech-recognition
|
| 17 |
name: Speech Recognition
|
| 18 |
dataset:
|
| 19 |
-
type: lsb/poetaexmachina-mp3-recitations
|
| 20 |
name: Poeta Ex Machina mp3 recitations
|
|
|
|
| 21 |
metrics:
|
| 22 |
- type: wer
|
| 23 |
value: 0.398
|
|
|
|
| 9 |
- lsb/poetaexmachina-mp3-recitations
|
| 10 |
metrics:
|
| 11 |
- wer
|
| 12 |
+
base_model: wav2vec2-base-it-voxpopuli
|
| 13 |
model-index:
|
| 14 |
- name: wav2vec2-base-it-latin
|
| 15 |
results:
|
|
|
|
| 17 |
type: automatic-speech-recognition
|
| 18 |
name: Speech Recognition
|
| 19 |
dataset:
|
|
|
|
| 20 |
name: Poeta Ex Machina mp3 recitations
|
| 21 |
+
type: lsb/poetaexmachina-mp3-recitations
|
| 22 |
metrics:
|
| 23 |
- type: wer
|
| 24 |
value: 0.398
|