Commit
•
8194103
1
Parent(s):
8d11d21
set lang
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ model = load_model(model_path)
|
|
| 41 |
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
|
| 42 |
sample = dataset[0]["audio"]["path"]
|
| 43 |
|
| 44 |
-
pred_out = transcribe(model, audio=sample)
|
| 45 |
print(pred_out["text"])
|
| 46 |
```
|
| 47 |
|
|
@@ -52,7 +52,7 @@ again.
|
|
| 52 |
To transcribe a local audio file, simply pass the path to the audio file as the `audio` argument to transcribe:
|
| 53 |
|
| 54 |
```python
|
| 55 |
-
pred_out = transcribe(model, audio="audio.mp3")
|
| 56 |
```
|
| 57 |
|
| 58 |
## CLI Usage
|
|
@@ -72,7 +72,7 @@ huggingface-cli download distil-whisper/distil-large-v3-openai model.bin --local
|
|
| 72 |
Finally, use the OpenAI Whisper CLI to transcribe:
|
| 73 |
|
| 74 |
```bash
|
| 75 |
-
whisper audio.mp3 --model distil-large-v3/model.bin
|
| 76 |
```
|
| 77 |
|
| 78 |
|
|
|
|
| 41 |
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
|
| 42 |
sample = dataset[0]["audio"]["path"]
|
| 43 |
|
| 44 |
+
pred_out = transcribe(model, audio=sample, language="en")
|
| 45 |
print(pred_out["text"])
|
| 46 |
```
|
| 47 |
|
|
|
|
| 52 |
To transcribe a local audio file, simply pass the path to the audio file as the `audio` argument to transcribe:
|
| 53 |
|
| 54 |
```python
|
| 55 |
+
pred_out = transcribe(model, audio="audio.mp3", language="en")
|
| 56 |
```
|
| 57 |
|
| 58 |
## CLI Usage
|
|
|
|
| 72 |
Finally, use the OpenAI Whisper CLI to transcribe:
|
| 73 |
|
| 74 |
```bash
|
| 75 |
+
whisper audio.mp3 --model distil-large-v3/model.bin --language en
|
| 76 |
```
|
| 77 |
|
| 78 |
|