Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,24 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- hi
|
5 |
+
pipeline_tag: automatic-speech-recognition
|
6 |
+
---
|
7 |
+
|
8 |
+
int8 quantized [ctranslate2](https://github.com/OpenNMT/CTranslate2)-compatible version of [vasista22/whisper-hindi-large-v2](https://huggingface.co/vasista22/whisper-hindi-large-v2).
|
9 |
+
This means the 5.7GB model is compressed into 1.6GB :).
|
10 |
+
|
11 |
+
Model created using
|
12 |
+
|
13 |
+
```
|
14 |
+
ct2-transformers-converter --model /path/to/vasista22/whisper-hindi-large-v2 --output_dir whisper-hindi-large-v2-ct2-int8 --copy_files tokenizer_config.json preprocessor_config.json added_tokens.json special_tokens_map.json --quantization int8
|
15 |
+
```
|
16 |
+
|
17 |
+
For monospeaker audio, use either of
|
18 |
+
|
19 |
+
1. [ctranslate2](https://github.com/OpenNMT/CTranslate2)
|
20 |
+
2. [faster-whisper](https://github.com/SYSTRAN/faster-whisper)
|
21 |
+
|
22 |
+
For multispeaker audio with english diarization, use [whisperX](https://github.com/m-bain/whisperX/).
|
23 |
+
|
24 |
+
For multispeaker audio with non-english diarization, use [whisper-diarization](https://github.com/MahmoudAshraf97/whisper-diarization/).
|