Instructions to use rossevine/Model_G_ALL_Wav2Vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rossevine/Model_G_ALL_Wav2Vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rossevine/Model_G_ALL_Wav2Vec2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("rossevine/Model_G_ALL_Wav2Vec2") model = AutoModelForCTC.from_pretrained("rossevine/Model_G_ALL_Wav2Vec2") - Notebooks
- Google Colab
- Kaggle
Upload lm-boosted decoder
Browse files
language_model/5gram_correct.arpa
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3745b5f78523d7792c4b6f885a7a9a741ac3d82084204e5d27443700f9aeea62
|
| 3 |
+
size 3962698644
|
language_model/attrs.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|