bayartsogt
commited on
Commit
•
2edd1f8
1
Parent(s):
db90892
Update README.md
Browse files
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
language: mn
|
3 |
datasets:
|
4 |
- common_voice
|
5 |
-
metrics:
|
6 |
-
- wer
|
7 |
tags:
|
8 |
- audio
|
9 |
- automatic-speech-recognition
|
@@ -11,15 +9,15 @@ tags:
|
|
11 |
- xlsr-fine-tuning-week
|
12 |
license: apache-2.0
|
13 |
model-index:
|
14 |
-
- name:
|
15 |
-
results:
|
16 |
- task:
|
17 |
name: Speech Recognition
|
18 |
type: automatic-speech-recognition
|
19 |
dataset:
|
20 |
-
name: Common Voice mn
|
21 |
type: common_voice
|
22 |
-
args: mn
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
@@ -51,15 +49,15 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
|
51 |
# Preprocessing the datasets.
|
52 |
# We need to read the aduio files as arrays
|
53 |
def speech_file_to_array_fn(batch):
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
|
58 |
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
59 |
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
60 |
|
61 |
with torch.no_grad():
|
62 |
-
|
63 |
|
64 |
predicted_ids = torch.argmax(logits, dim=-1)
|
65 |
|
@@ -86,31 +84,31 @@ processor = Wav2Vec2Processor.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mo
|
|
86 |
model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian")
|
87 |
model.to("cuda")
|
88 |
|
89 |
-
chars_to_ignore_regex = '[
|
90 |
|
91 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
92 |
|
93 |
# Preprocessing the datasets.
|
94 |
# We need to read the aduio files as arrays
|
95 |
def speech_file_to_array_fn(batch):
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
|
101 |
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
102 |
|
103 |
# Preprocessing the datasets.
|
104 |
# We need to read the aduio files as arrays
|
105 |
def evaluate(batch):
|
106 |
-
|
107 |
|
108 |
-
|
109 |
-
|
110 |
|
111 |
pred_ids = torch.argmax(logits, dim=-1)
|
112 |
-
|
113 |
-
|
114 |
|
115 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
116 |
|
|
|
2 |
language: mn
|
3 |
datasets:
|
4 |
- common_voice
|
|
|
|
|
5 |
tags:
|
6 |
- audio
|
7 |
- automatic-speech-recognition
|
|
|
9 |
- xlsr-fine-tuning-week
|
10 |
license: apache-2.0
|
11 |
model-index:
|
12 |
+
- name: XLSR Wav2Vec2 Mongolian by Bayartsogt
|
13 |
+
results:
|
14 |
- task:
|
15 |
name: Speech Recognition
|
16 |
type: automatic-speech-recognition
|
17 |
dataset:
|
18 |
+
name: Common Voice mn
|
19 |
type: common_voice
|
20 |
+
args: mn
|
21 |
metrics:
|
22 |
- name: Test WER
|
23 |
type: wer
|
|
|
49 |
# Preprocessing the datasets.
|
50 |
# We need to read the aduio files as arrays
|
51 |
def speech_file_to_array_fn(batch):
|
52 |
+
\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
|
53 |
+
\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
|
54 |
+
\\treturn batch
|
55 |
|
56 |
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
57 |
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
|
58 |
|
59 |
with torch.no_grad():
|
60 |
+
\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
61 |
|
62 |
predicted_ids = torch.argmax(logits, dim=-1)
|
63 |
|
|
|
84 |
model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian")
|
85 |
model.to("cuda")
|
86 |
|
87 |
+
chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\'h\\\\«\\\\»]'
|
88 |
|
89 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
90 |
|
91 |
# Preprocessing the datasets.
|
92 |
# We need to read the aduio files as arrays
|
93 |
def speech_file_to_array_fn(batch):
|
94 |
+
\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
95 |
+
\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
|
96 |
+
\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
|
97 |
+
\\treturn batch
|
98 |
|
99 |
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
100 |
|
101 |
# Preprocessing the datasets.
|
102 |
# We need to read the aduio files as arrays
|
103 |
def evaluate(batch):
|
104 |
+
\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
105 |
|
106 |
+
\\twith torch.no_grad():
|
107 |
+
\\t\\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
|
108 |
|
109 |
pred_ids = torch.argmax(logits, dim=-1)
|
110 |
+
\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
|
111 |
+
\\treturn batch
|
112 |
|
113 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
114 |
|