Instructions to use pirxus/wav2vec2_s2t_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pirxus/wav2vec2_s2t_encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="pirxus/wav2vec2_s2t_encoder")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("pirxus/wav2vec2_s2t_encoder") model = AutoModelForCTC.from_pretrained("pirxus/wav2vec2_s2t_encoder") - Notebooks
- Google Colab
- Kaggle
Upload Wav2Vec2ForCTC
Browse files- config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -27,7 +27,7 @@
|
|
| 27 |
2
|
| 28 |
],
|
| 29 |
"ctc_loss_reduction": "sum",
|
| 30 |
-
"ctc_zero_infinity":
|
| 31 |
"diversity_loss_weight": 0.1,
|
| 32 |
"do_stable_layer_norm": false,
|
| 33 |
"eos_token_id": 2,
|
|
|
|
| 27 |
2
|
| 28 |
],
|
| 29 |
"ctc_loss_reduction": "sum",
|
| 30 |
+
"ctc_zero_infinity": true,
|
| 31 |
"diversity_loss_weight": 0.1,
|
| 32 |
"do_stable_layer_norm": false,
|
| 33 |
"eos_token_id": 2,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 66339736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7af1ea02b161e230de7e82aa9046af417f558042b5e986ac2012393a9dcbd3e4
|
| 3 |
size 66339736
|