Instructions to use skypro1111/mbart-large-50-verbalization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use skypro1111/mbart-large-50-verbalization with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("skypro1111/mbart-large-50-verbalization") model = AutoModelForSeq2SeqLM.from_pretrained("skypro1111/mbart-large-50-verbalization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -108,6 +108,168 @@ output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
|
|
| 108 |
print(output_text)
|
| 109 |
```
|
| 110 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
## Performance
|
| 112 |
Evaluation metrics were not explicitly used for this model. Its performance is primarily demonstrated through its application in enhancing the naturalness of TTS outputs.
|
| 113 |
|
|
|
|
| 108 |
print(output_text)
|
| 109 |
```
|
| 110 |
|
| 111 |
+
## ONNX usage
|
| 112 |
+
```bash
|
| 113 |
+
poetry new verbalizer
|
| 114 |
+
rm -rf verbalizer/tests/ verbalizer/verbalizer/ verbalizer/README.md
|
| 115 |
+
cd verbalizer/
|
| 116 |
+
poetry shell
|
| 117 |
+
wget https://huggingface.co/skypro1111/mbart-large-50-verbalization/resolve/main/onnx/infer_onnx_hf.py
|
| 118 |
+
poetry add transformers huggingface_hub onnxruntime-gpu torch
|
| 119 |
+
python infer_onnx_hf.py
|
| 120 |
+
```
|
| 121 |
+
|
| 122 |
+
```python
|
| 123 |
+
import onnxruntime
|
| 124 |
+
import numpy as np
|
| 125 |
+
from transformers import AutoTokenizer
|
| 126 |
+
import time
|
| 127 |
+
import os
|
| 128 |
+
from huggingface_hub import hf_hub_download
|
| 129 |
+
|
| 130 |
+
model_name = "skypro1111/mbart-large-50-verbalization"
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
def download_model_from_hf(repo_id=model_name, model_dir="onnx_hf"):
|
| 134 |
+
"""Download ONNX models from HuggingFace Hub."""
|
| 135 |
+
os.makedirs(model_dir, exist_ok=True)
|
| 136 |
+
|
| 137 |
+
files = ["onnx/encoder_model.onnx", "onnx/decoder_model.onnx", "onnx/decoder_model.onnx_data"]
|
| 138 |
+
|
| 139 |
+
for file in files:
|
| 140 |
+
hf_hub_download(
|
| 141 |
+
repo_id=repo_id,
|
| 142 |
+
filename=file,
|
| 143 |
+
local_dir=model_dir
|
| 144 |
+
)
|
| 145 |
+
|
| 146 |
+
return files
|
| 147 |
+
|
| 148 |
+
def create_onnx_session(model_path, use_gpu=True):
|
| 149 |
+
"""Create an ONNX inference session."""
|
| 150 |
+
# Session options
|
| 151 |
+
session_options = onnxruntime.SessionOptions()
|
| 152 |
+
session_options.graph_optimization_level = onnxruntime.GraphOptimizationLevel.ORT_ENABLE_ALL
|
| 153 |
+
session_options.enable_mem_pattern = True
|
| 154 |
+
session_options.enable_mem_reuse = True
|
| 155 |
+
session_options.intra_op_num_threads = 8
|
| 156 |
+
session_options.log_severity_level = 1
|
| 157 |
+
|
| 158 |
+
cuda_provider_options = {
|
| 159 |
+
'device_id': 0,
|
| 160 |
+
'arena_extend_strategy': 'kSameAsRequested',
|
| 161 |
+
'gpu_mem_limit': 0, # 0 means no limit
|
| 162 |
+
'cudnn_conv_algo_search': 'DEFAULT',
|
| 163 |
+
'do_copy_in_default_stream': True,
|
| 164 |
+
}
|
| 165 |
+
|
| 166 |
+
print(f"Available providers: {onnxruntime.get_available_providers()}")
|
| 167 |
+
if use_gpu and 'CUDAExecutionProvider' in onnxruntime.get_available_providers():
|
| 168 |
+
providers = [('CUDAExecutionProvider', cuda_provider_options)]
|
| 169 |
+
print("Using CUDA for inference")
|
| 170 |
+
else:
|
| 171 |
+
providers = ['CPUExecutionProvider']
|
| 172 |
+
print("Using CPU for inference")
|
| 173 |
+
|
| 174 |
+
session = onnxruntime.InferenceSession(
|
| 175 |
+
model_path,
|
| 176 |
+
providers=providers,
|
| 177 |
+
sess_options=session_options
|
| 178 |
+
)
|
| 179 |
+
|
| 180 |
+
return session
|
| 181 |
+
|
| 182 |
+
def generate_text(text, tokenizer, encoder_session, decoder_session, max_length=128):
|
| 183 |
+
"""Generate text for a single input."""
|
| 184 |
+
# Prepare input
|
| 185 |
+
inputs = tokenizer(text, return_tensors="np", padding=True, truncation=True, max_length=512)
|
| 186 |
+
input_ids = inputs["input_ids"].astype(np.int64)
|
| 187 |
+
attention_mask = inputs["attention_mask"].astype(np.int64)
|
| 188 |
+
|
| 189 |
+
# Run encoder
|
| 190 |
+
encoder_outputs = encoder_session.run(
|
| 191 |
+
output_names=["last_hidden_state"],
|
| 192 |
+
input_feed={
|
| 193 |
+
"input_ids": input_ids,
|
| 194 |
+
"attention_mask": attention_mask,
|
| 195 |
+
}
|
| 196 |
+
)[0]
|
| 197 |
+
|
| 198 |
+
# Initialize decoder input
|
| 199 |
+
decoder_input_ids = np.array([[tokenizer.pad_token_id]], dtype=np.int64)
|
| 200 |
+
|
| 201 |
+
# Generate sequence
|
| 202 |
+
for _ in range(max_length):
|
| 203 |
+
# Run decoder
|
| 204 |
+
decoder_outputs = decoder_session.run(
|
| 205 |
+
output_names=["logits"],
|
| 206 |
+
input_feed={
|
| 207 |
+
"input_ids": decoder_input_ids,
|
| 208 |
+
"encoder_hidden_states": encoder_outputs,
|
| 209 |
+
"encoder_attention_mask": attention_mask,
|
| 210 |
+
}
|
| 211 |
+
)[0]
|
| 212 |
+
|
| 213 |
+
# Get next token
|
| 214 |
+
next_token = decoder_outputs[:, -1:].argmax(axis=-1)
|
| 215 |
+
decoder_input_ids = np.concatenate([decoder_input_ids, next_token], axis=-1)
|
| 216 |
+
|
| 217 |
+
# Check if sequence is complete
|
| 218 |
+
if tokenizer.eos_token_id in decoder_input_ids[0]:
|
| 219 |
+
break
|
| 220 |
+
|
| 221 |
+
# Decode sequence
|
| 222 |
+
output_text = tokenizer.decode(decoder_input_ids[0], skip_special_tokens=True)
|
| 223 |
+
return output_text
|
| 224 |
+
|
| 225 |
+
def main():
|
| 226 |
+
# Print available providers
|
| 227 |
+
print("Available providers:", onnxruntime.get_available_providers())
|
| 228 |
+
|
| 229 |
+
# Download models from HuggingFace
|
| 230 |
+
print("\nDownloading models from HuggingFace...")
|
| 231 |
+
encoder_path, decoder_path, _ = download_model_from_hf()
|
| 232 |
+
|
| 233 |
+
# Load tokenizer and models
|
| 234 |
+
print("\nLoading tokenizer...")
|
| 235 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 236 |
+
tokenizer.src_lang = "uk_UA"
|
| 237 |
+
tokenizer.tgt_lang = "uk_UA"
|
| 238 |
+
|
| 239 |
+
# Create ONNX sessions
|
| 240 |
+
print("\nLoading encoder...")
|
| 241 |
+
encoder_session = create_onnx_session(encoder_path)
|
| 242 |
+
print("\nLoading decoder...")
|
| 243 |
+
decoder_session = create_onnx_session(decoder_path)
|
| 244 |
+
|
| 245 |
+
# Test examples
|
| 246 |
+
test_inputs = [
|
| 247 |
+
"мій телефон 0979456822",
|
| 248 |
+
"квартира площею 11 тис кв м.",
|
| 249 |
+
"Пропонували хабар у 1 млрд грн.",
|
| 250 |
+
"1 2 3 4 5 6 7 8 9 10.",
|
| 251 |
+
"Крім того, парламентарій володіє шістьма ділянками землі (дві площею 25000 кв м, дві по 15000 кв м та дві по 10000 кв м) розташованими в Сосновій Балці Луганської області.",
|
| 252 |
+
"Підписуючи цей документ у 2003 році, голови Росії та України мали намір зміцнити співпрацю та сприяти розширенню двосторонніх відносин.",
|
| 253 |
+
"Очікується, що цей застосунок буде запущено 22.08.2025.",
|
| 254 |
+
"За інформацією від Державної служби з надзвичайних ситуацій станом на 7 ранку 15 липня.",
|
| 255 |
+
]
|
| 256 |
+
|
| 257 |
+
print("\nWarming up...")
|
| 258 |
+
_ = generate_text(test_inputs[0], tokenizer, encoder_session, decoder_session)
|
| 259 |
+
|
| 260 |
+
print("\nRunning inference...")
|
| 261 |
+
for text in test_inputs:
|
| 262 |
+
print(f"\nInput: {text}")
|
| 263 |
+
t = time.time()
|
| 264 |
+
output = generate_text(text, tokenizer, encoder_session, decoder_session)
|
| 265 |
+
print(f"Output: {output}")
|
| 266 |
+
print(f"Time: {time.time() - t:.2f} seconds")
|
| 267 |
+
|
| 268 |
+
if __name__ == "__main__":
|
| 269 |
+
main()
|
| 270 |
+
```
|
| 271 |
+
|
| 272 |
+
|
| 273 |
## Performance
|
| 274 |
Evaluation metrics were not explicitly used for this model. Its performance is primarily demonstrated through its application in enhancing the naturalness of TTS outputs.
|
| 275 |
|