pyf98 commited on
Commit
437a576
1 Parent(s): 24122a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -20,7 +20,8 @@ Currently, the code for OWSM-CTC has not been merged into ESPnet main branch. In
20
  - Code in my repo: https://github.com/pyf98/espnet/tree/owsm-ctc
21
  - Current model on HF: https://huggingface.co/pyf98/owsm_ctc_v3.1_1B
22
 
23
- An example script to run short-form ASR/ST:
 
24
  ```python
25
  import soundfile as sf
26
  import numpy as np
@@ -46,7 +47,8 @@ res = s2t(speech)[0]
46
  print(res)
47
  ```
48
 
49
- An example script to run long-form ASR:
 
50
  ```python
51
  import soundfile as sf
52
  import torch
@@ -77,7 +79,9 @@ if __name__ == "__main__":
77
  print(text)
78
  ```
79
 
80
- An example for CTC forced alignment using `ctc-segmentation`. It can be efficiently applied to audio of an arbitrary length.
 
 
81
  For model downloading, please refer to https://github.com/espnet/espnet?tab=readme-ov-file#ctc-segmentation-demo
82
 
83
  ```python
 
20
  - Code in my repo: https://github.com/pyf98/espnet/tree/owsm-ctc
21
  - Current model on HF: https://huggingface.co/pyf98/owsm_ctc_v3.1_1B
22
 
23
+ ### Example script for short-form ASR/ST
24
+
25
  ```python
26
  import soundfile as sf
27
  import numpy as np
 
47
  print(res)
48
  ```
49
 
50
+ ### Example script for long-form ASR/ST
51
+
52
  ```python
53
  import soundfile as sf
54
  import torch
 
79
  print(text)
80
  ```
81
 
82
+ ### Example for CTC forced alignment using `ctc-segmentation`
83
+
84
+ It can be efficiently applied to audio of an arbitrary length.
85
  For model downloading, please refer to https://github.com/espnet/espnet?tab=readme-ov-file#ctc-segmentation-demo
86
 
87
  ```python