jonatasgrosman
commited on
Commit
•
0781a6f
1
Parent(s):
f758bc3
Update README.md
Browse files
README.md
CHANGED
@@ -132,14 +132,14 @@ test_dataset = test_dataset.map(speech_file_to_array_fn)
|
|
132 |
# Preprocessing the datasets.
|
133 |
# We need to read the audio files as arrays
|
134 |
def evaluate(batch):
|
135 |
-
|
136 |
|
137 |
-
|
138 |
-
|
139 |
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
|
144 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
145 |
|
@@ -158,4 +158,5 @@ My model may report better scores than others because of some specificity of my
|
|
158 |
| ------------- | ------------- | ------------- |
|
159 |
| jonatasgrosman/wav2vec2-large-xlsr-53-hungarian | **31.40%** | **6.20%** |
|
160 |
| anton-l/wav2vec2-large-xlsr-53-hungarian | 42.39% | 9.39% |
|
|
|
161 |
| birgermoell/wav2vec2-large-xlsr-hungarian | 46.93% | 10.31% |
|
|
|
132 |
# Preprocessing the datasets.
|
133 |
# We need to read the audio files as arrays
|
134 |
def evaluate(batch):
|
135 |
+
\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
136 |
|
137 |
+
\\twith torch.no_grad():
|
138 |
+
\\t\\tlogits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits
|
139 |
|
140 |
+
\\tpred_ids = torch.argmax(logits, dim=-1)
|
141 |
+
\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
|
142 |
+
\\treturn batch
|
143 |
|
144 |
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
145 |
|
|
|
158 |
| ------------- | ------------- | ------------- |
|
159 |
| jonatasgrosman/wav2vec2-large-xlsr-53-hungarian | **31.40%** | **6.20%** |
|
160 |
| anton-l/wav2vec2-large-xlsr-53-hungarian | 42.39% | 9.39% |
|
161 |
+
| gchhablani/wav2vec2-large-xlsr-hu | 46.42% | 10.04% |
|
162 |
| birgermoell/wav2vec2-large-xlsr-hungarian | 46.93% | 10.31% |
|