Update README.md
Browse files
README.md
CHANGED
|
@@ -14,13 +14,19 @@ This repository contains the conversion of [kotoba-tech/kotoba-whisper-v1.0](htt
|
|
| 14 |
This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper).
|
| 15 |
|
| 16 |
## Example
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
```python
|
| 19 |
from faster_whisper import WhisperModel
|
| 20 |
|
| 21 |
-
model = WhisperModel("kotoba-tech/kotoba-whisper-v1.0")
|
| 22 |
|
| 23 |
-
segments, info = model.transcribe("
|
| 24 |
for segment in segments:
|
| 25 |
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
|
| 26 |
```
|
|
@@ -30,7 +36,7 @@ for segment in segments:
|
|
| 30 |
The original model was converted with the following command:
|
| 31 |
|
| 32 |
```
|
| 33 |
-
ct2-transformers-converter --model kotoba-tech/kotoba-whisper-v1.0 --output_dir
|
| 34 |
--copy_files tokenizer.json preprocessor_config.json --quantization float16
|
| 35 |
```
|
| 36 |
|
|
|
|
| 14 |
This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper).
|
| 15 |
|
| 16 |
## Example
|
| 17 |
+
Install library and download sample audio.
|
| 18 |
+
```shell
|
| 19 |
+
pip install faster-whisper
|
| 20 |
+
wget https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/resolve/main/sample_ja_speech.wav
|
| 21 |
+
```
|
| 22 |
+
Inference with the kotoba-whisper-v1.0-faster.
|
| 23 |
|
| 24 |
```python
|
| 25 |
from faster_whisper import WhisperModel
|
| 26 |
|
| 27 |
+
model = WhisperModel("kotoba-tech/kotoba-whisper-v1.0-faster")
|
| 28 |
|
| 29 |
+
segments, info = model.transcribe("sample_ja_speech.wav")
|
| 30 |
for segment in segments:
|
| 31 |
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
|
| 32 |
```
|
|
|
|
| 36 |
The original model was converted with the following command:
|
| 37 |
|
| 38 |
```
|
| 39 |
+
ct2-transformers-converter --model kotoba-tech/kotoba-whisper-v1.0 --output_dir kotoba-whisper-v1.0-faster \
|
| 40 |
--copy_files tokenizer.json preprocessor_config.json --quantization float16
|
| 41 |
```
|
| 42 |
|