Instructions to use emon1521/wav2vec2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use emon1521/wav2vec2-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="emon1521/wav2vec2-base")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("emon1521/wav2vec2-base") model = AutoModelForCTC.from_pretrained("emon1521/wav2vec2-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
add tokenizer
Browse files
runs/Apr06_10-24-33_DESKTOP-5GECLH7/1649219150.819579/events.out.tfevents.1649219150.DESKTOP-5GECLH7.20404.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e90cff95c543ff1a60df3f6f5675a027c012554cf9df6e00947522193db1c9c
|
| 3 |
+
size 4507
|
runs/Apr06_10-24-33_DESKTOP-5GECLH7/events.out.tfevents.1649219150.DESKTOP-5GECLH7.20404.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dd9d099c6b23f1464e78df989d1b358860a578c6d342a88d5cb8264193cf97f
|
| 3 |
+
size 4437
|
vocab.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"
|
|
|
|
| 1 |
+
{"h": 0, "w": 1, "a": 2, "d": 3, "c": 4, "x": 5, "r": 6, "i": 7, "f": 8, "b": 9, "q": 10, "s": 11, "t": 12, "l": 13, "z": 15, "y": 16, "m": 17, "u": 18, "k": 19, "v": 20, "e": 21, "p": 22, "o": 23, "j": 24, "n": 25, "g": 26, "'": 27, "|": 14, "[UNK]": 28, "[PAD]": 29}
|