Oblivion208
commited on
Commit
•
3a521bf
1
Parent(s):
41fe0a6
Update README.md
Browse files
README.md
CHANGED
@@ -14,6 +14,39 @@ pipeline_tag: automatic-speech-recognition
|
|
14 |
🤗 <a href="https://huggingface.co/Oblivion208" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/fengredrum/finetune-whisper-lora" target="_blank">Github Repo</a>
|
15 |
</p>
|
16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
## Approximate Performance Evaluation
|
18 |
|
19 |
The following models are all trained and evaluated on a single RTX 3090 GPU.
|
|
|
14 |
🤗 <a href="https://huggingface.co/Oblivion208" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/fengredrum/finetune-whisper-lora" target="_blank">Github Repo</a>
|
15 |
</p>
|
16 |
|
17 |
+
## Usage
|
18 |
+
```python
|
19 |
+
import torch
|
20 |
+
import librosa
|
21 |
+
from transformers import WhisperProcessor, WhisperTokenizer, WhisperForConditionalGeneration
|
22 |
+
|
23 |
+
# Setups
|
24 |
+
model_name_or_path = "Oblivion208/whisper-tiny-cantonese"
|
25 |
+
task = "transcribe"
|
26 |
+
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
27 |
+
|
28 |
+
model = WhisperForConditionalGeneration.from_pretrained(model_name_or_path).to(device)
|
29 |
+
tokenizer = WhisperTokenizer.from_pretrained(model_name_or_path, task=task)
|
30 |
+
processor = WhisperProcessor.from_pretrained(model_name_or_path, task=task)
|
31 |
+
feature_extractor = processor.feature_extractor
|
32 |
+
model.config.forced_decoder_ids = None
|
33 |
+
model.config.suppress_tokens = []
|
34 |
+
|
35 |
+
filepath = 'test.wav'
|
36 |
+
audio, sr = librosa.load(filepath, sr=16000, mono=True)
|
37 |
+
inputs = processor(audio, sample_rate=sr, return_tensors="pt").to(device)
|
38 |
+
|
39 |
+
with torch.inference_mode():
|
40 |
+
generated_tokens = model.generate(
|
41 |
+
input_features=inputs.input_features,
|
42 |
+
return_dict_in_generate=True,
|
43 |
+
max_new_tokens=255,
|
44 |
+
)
|
45 |
+
transcription = tokenizer.batch_decode(
|
46 |
+
generated_tokens.sequences, skip_special_tokens=True)
|
47 |
+
print(transcription)
|
48 |
+
```
|
49 |
+
|
50 |
## Approximate Performance Evaluation
|
51 |
|
52 |
The following models are all trained and evaluated on a single RTX 3090 GPU.
|