File size: 740 Bytes
79a0935
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c4574c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
---
language:
- as
- bn
- brx
- doi
- gu
- hi
- kn
- kok
- ks
- mai
- ml
- mni
- mr
- ne
- or
- pa
- sa
- sat
- sd
- ta
- te
- ur
pipeline_tag: automatic-speech-recognition
library_name: transformers
---

```bash
pip install -q torch_state_bridge srt webrtcvad torchcodec
```

```python
from transformers import AutoModel
model = AutoModel.from_pretrained("shethjenil/Indic-STT", language="hi", trust_remote_code=True, dtype="auto")
wav , sr = torchaudio.load("audio.wav")
for i in model.transcribe(wav,sr,4):
    print("".join(i.splitlines()[2::4]).replace("▁"," ").replace("<line>","\n"))

```

```python
full_model = AutoModel.from_pretrained("shethjenil/Indic-STT", trust_remote_code=True, dtype="auto")
full_model.language = "hi"
```