Upload folder using huggingface_hub
Browse files- README.md +19 -0
- model.weights.h5 +3 -0
- spm.model +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: automatic-speech-recognition
|
| 3 |
+
license: mit
|
| 4 |
+
library_name: kerasformers
|
| 5 |
+
tags:
|
| 6 |
+
- keras
|
| 7 |
+
- kerasformers
|
| 8 |
+
- speech2text
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# s2t-medium-librispeech-asr (Keras 3)
|
| 12 |
+
|
| 13 |
+
Pure-Keras 3 weights for [kerasformers](https://github.com/IMvision12/KerasFormers), mirrored from the GitHub release. License: `mit`.
|
| 14 |
+
|
| 15 |
+
```python
|
| 16 |
+
from kerasformers.models.speech2text import Speech2TextSpeechToText, Speech2TextProcessor
|
| 17 |
+
model = Speech2TextSpeechToText.from_weights("s2t-medium-librispeech-asr")
|
| 18 |
+
processor = Speech2TextProcessor.from_weights("s2t-medium-librispeech-asr")
|
| 19 |
+
```
|
model.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86925f0a2422d43328b2aab2b2b1661552b8d6b450c8d14febf46dd03400d88d
|
| 3 |
+
size 320413256
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:052a168787a9160b4b2ba54e4995e9600298812c34191ca3f70cea51cd4f5c1e
|
| 3 |
+
size 416684
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|