Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
datasets:
|
4 |
- common_voice
|
5 |
metrics:
|
@@ -11,19 +11,19 @@ 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
|
21 |
-
type: common_voice
|
22 |
-
args:
|
23 |
-
metrics:
|
24 |
-
- name: Test WER
|
25 |
-
type: wer
|
26 |
-
value:
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-53-Tatar
|
@@ -51,15 +51,15 @@ 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 |
-
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
55 |
-
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
56 |
-
return batch
|
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 |
-
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
63 |
|
64 |
predicted_ids = torch.argmax(logits, dim=-1)
|
65 |
|
@@ -93,24 +93,24 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
|
93 |
# Preprocessing the datasets.
|
94 |
# We need to read the aduio files as arrays
|
95 |
def speech_file_to_array_fn(batch):
|
96 |
-
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
97 |
-
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
98 |
-
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
99 |
-
return batch
|
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 |
-
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
107 |
|
108 |
-
with torch.no_grad():
|
109 |
-
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
|
110 |
|
111 |
-
pred_ids = torch.argmax(logits, dim=-1)
|
112 |
-
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
113 |
-
return batch
|
114 |
|
115 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
116 |
|
@@ -122,4 +122,4 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
|
|
122 |
|
123 |
## Training
|
124 |
|
125 |
-
The Common Voice `train` and `validation` datasets were used for training.
|
|
|
1 |
---
|
2 |
+
language: tt
|
3 |
datasets:
|
4 |
- common_voice
|
5 |
metrics:
|
|
|
11 |
- xlsr-fine-tuning-week
|
12 |
license: apache-2.0
|
13 |
model-index:
|
14 |
+
- name: Tatar XLSR Wav2Vec2 Large 53
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Common Voice tt
|
21 |
+
type: common_voice
|
22 |
+
args: tt
|
23 |
+
metrics:
|
24 |
+
- name: Test WER
|
25 |
+
type: wer
|
26 |
+
value: 30.93
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-53-Tatar
|
|
|
51 |
# Preprocessing the datasets.
|
52 |
# We need to read the aduio files as arrays
|
53 |
def speech_file_to_array_fn(batch):
|
54 |
+
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
55 |
+
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
56 |
+
return batch
|
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 |
+
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
63 |
|
64 |
predicted_ids = torch.argmax(logits, dim=-1)
|
65 |
|
|
|
93 |
# Preprocessing the datasets.
|
94 |
# We need to read the aduio files as arrays
|
95 |
def speech_file_to_array_fn(batch):
|
96 |
+
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
97 |
+
speech_array, sampling_rate = torchaudio.load(batch["path"])
|
98 |
+
batch["speech"] = resampler(speech_array).squeeze().numpy()
|
99 |
+
return batch
|
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 |
+
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
107 |
|
108 |
+
with torch.no_grad():
|
109 |
+
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
|
110 |
|
111 |
+
pred_ids = torch.argmax(logits, dim=-1)
|
112 |
+
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
113 |
+
return batch
|
114 |
|
115 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
116 |
|
|
|
122 |
|
123 |
## Training
|
124 |
|
125 |
+
The Common Voice `train` and `validation` datasets were used for training.
|