facebook
/
wav2vec2-base-960h
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Patrick von Platen 2022-04-05 16:39:29 +00:00 committed by huggingface-web
parent 5962bda7bb
commit c0b7a4ab9d
1 changed files with 1 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -81,7 +81,6 @@ To transcribe audio files the model can be used as a standalone acoustic model a
```python ```python
from datasets import load_dataset from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import soundfile as sf
import torch import torch
from jiwer import wer from jiwer import wer
@ -91,15 +90,8 @@ librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda") model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
def map_to_array(batch):
speech, _ = sf.read(batch["file"])
batch["speech"] = speech
return batch
librispeech_eval = librispeech_eval.map(map_to_array)
def map_to_pred(batch): def map_to_pred(batch):
input_values = processor(batch["speech"], return_tensors="pt", padding="longest").input_values input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values
with torch.no_grad(): with torch.no_grad():
logits = model(input_values.to("cuda")).logits logits = model(input_values.to("cuda")).logits