Commit
•
e517d24
1
Parent(s):
78add66
Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,11 @@ tags:
|
|
6 |
- speech
|
7 |
- audio
|
8 |
- automatic-speech-recognition
|
|
|
|
|
|
|
|
|
|
|
9 |
license: apache-2.0
|
10 |
---
|
11 |
|
@@ -59,52 +64,4 @@ To transcribe audio files the model can be used as a standalone acoustic model a
|
|
59 |
# take argmax and decode
|
60 |
predicted_ids = torch.argmax(logits, dim=-1)
|
61 |
transcription = processor.batch_decode(predicted_ids)
|
62 |
-
```
|
63 |
-
|
64 |
-
## Evaluation
|
65 |
-
|
66 |
-
This code snippet shows how to evaluate **facebook/wav2vec2-large-960h-lv60-self** on LibriSpeech's "clean" and "other" test data.
|
67 |
-
|
68 |
-
```python
|
69 |
-
from datasets import load_dataset
|
70 |
-
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
71 |
-
import soundfile as sf
|
72 |
-
import torch
|
73 |
-
from jiwer import wer
|
74 |
-
|
75 |
-
|
76 |
-
librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
|
77 |
-
|
78 |
-
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self").to("cuda")
|
79 |
-
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
|
80 |
-
|
81 |
-
def map_to_array(batch):
|
82 |
-
speech, _ = sf.read(batch["file"])
|
83 |
-
batch["speech"] = speech
|
84 |
-
return batch
|
85 |
-
|
86 |
-
librispeech_eval = librispeech_eval.map(map_to_array)
|
87 |
-
|
88 |
-
def map_to_pred(batch):
|
89 |
-
inputs = processor(batch["speech"], return_tensors="pt", padding="longest")
|
90 |
-
input_values = inputs.input_values.to("cuda")
|
91 |
-
attention_mask = inputs.attention_mask.to("cuda")
|
92 |
-
|
93 |
-
with torch.no_grad():
|
94 |
-
logits = model(input_values, attention_mask=attention_mask).logits
|
95 |
-
|
96 |
-
predicted_ids = torch.argmax(logits, dim=-1)
|
97 |
-
transcription = processor.batch_decode(predicted_ids)
|
98 |
-
batch["transcription"] = transcription
|
99 |
-
return batch
|
100 |
-
|
101 |
-
result = librispeech_eval.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
|
102 |
-
|
103 |
-
print("WER:", wer(result["text"], result["transcription"]))
|
104 |
-
```
|
105 |
-
|
106 |
-
*Result (WER)*:
|
107 |
-
|
108 |
-
| "clean" | "other" |
|
109 |
-
|---|---|
|
110 |
-
| 1.9 | 3.9 |
|
|
|
6 |
- speech
|
7 |
- audio
|
8 |
- automatic-speech-recognition
|
9 |
+
widget:
|
10 |
+
- label: Librispeech sample 1
|
11 |
+
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
|
12 |
+
- label: Librispeech sample 2
|
13 |
+
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
|
14 |
license: apache-2.0
|
15 |
---
|
16 |
|
|
|
64 |
# take argmax and decode
|
65 |
predicted_ids = torch.argmax(logits, dim=-1)
|
66 |
transcription = processor.batch_decode(predicted_ids)
|
67 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|