Commit
•
eeb61f6
1
Parent(s):
a8b7a5f
oai whisper language
Browse files
README.md
CHANGED
@@ -543,7 +543,7 @@ model = load_model(model_path)
|
|
543 |
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
|
544 |
sample = dataset[0]["audio"]["path"]
|
545 |
|
546 |
-
pred_out = transcribe(model, audio=sample)
|
547 |
print(pred_out["text"])
|
548 |
```
|
549 |
|
@@ -554,7 +554,7 @@ again.
|
|
554 |
To transcribe a local audio file, simply pass the path to the audio file as the `audio` argument to transcribe:
|
555 |
|
556 |
```python
|
557 |
-
pred_out = transcribe(model, audio="
|
558 |
```
|
559 |
|
560 |
The Distil-Whisper model can also be used with the OpenAI Whisper CLI. Refer to the [following instructions](https://huggingface.co/distil-whisper/distil-large-v3-openai#cli-usage)
|
|
|
543 |
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
|
544 |
sample = dataset[0]["audio"]["path"]
|
545 |
|
546 |
+
pred_out = transcribe(model, audio=sample, language="en")
|
547 |
print(pred_out["text"])
|
548 |
```
|
549 |
|
|
|
554 |
To transcribe a local audio file, simply pass the path to the audio file as the `audio` argument to transcribe:
|
555 |
|
556 |
```python
|
557 |
+
pred_out = transcribe(model, audio=sample, language="en")
|
558 |
```
|
559 |
|
560 |
The Distil-Whisper model can also be used with the OpenAI Whisper CLI. Refer to the [following instructions](https://huggingface.co/distil-whisper/distil-large-v3-openai#cli-usage)
|