Commit
·
a6e5db9
1
Parent(s):
964ddc3
update README
Browse files
README.md
CHANGED
|
@@ -101,15 +101,12 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
|
| 101 |
LANG_ID = "ja"
|
| 102 |
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-japanese"
|
| 103 |
DEVICE = "cuda"
|
| 104 |
-
MAX_SAMPLES = 8000
|
| 105 |
|
| 106 |
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
|
| 107 |
"؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
|
| 108 |
"=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
|
| 109 |
|
| 110 |
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
|
| 111 |
-
if len(test_dataset) > MAX_SAMPLES:
|
| 112 |
-
test_dataset = test_dataset.select(range(MAX_SAMPLES))
|
| 113 |
|
| 114 |
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
|
| 115 |
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
|
|
|
|
| 101 |
LANG_ID = "ja"
|
| 102 |
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-japanese"
|
| 103 |
DEVICE = "cuda"
|
|
|
|
| 104 |
|
| 105 |
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
|
| 106 |
"؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
|
| 107 |
"=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
|
| 108 |
|
| 109 |
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
|
|
|
|
|
|
|
| 110 |
|
| 111 |
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
|
| 112 |
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
|