Upload folder using huggingface_hub
Browse files- README.md +15 -15
- onnx/tokenizer.json +0 -0
README.md
CHANGED
|
@@ -3,18 +3,18 @@ language:
|
|
| 3 |
- vi
|
| 4 |
license: mit
|
| 5 |
library_name: onnx
|
| 6 |
-
pipeline_tag:
|
| 7 |
tags:
|
| 8 |
-
- text2text-generation
|
| 9 |
-
- onnx
|
| 10 |
-
- vietnamese
|
| 11 |
-
- teencode
|
| 12 |
-
- text-normalization
|
| 13 |
-
- seq2seq
|
| 14 |
-
- int8
|
| 15 |
-
- raspberry-pi
|
| 16 |
model-index:
|
| 17 |
-
- name:
|
| 18 |
results:
|
| 19 |
- task:
|
| 20 |
type: text2text-generation
|
|
@@ -31,9 +31,9 @@ model-index:
|
|
| 31 |
|
| 32 |
# teencode-normalizer v3
|
| 33 |
|
| 34 |
-
Encoder
|
| 35 |
|
| 36 |
-
Code (Rust data prep / inference / HTTP server, Python training, Pi Docker, Colab): https://github.com/
|
| 37 |
|
| 38 |
## Files
|
| 39 |
|
|
@@ -94,8 +94,8 @@ The context test set comes from the same generator as the context training data,
|
|
| 94 |
### Rust runner (recommended: beam 4 + guard)
|
| 95 |
|
| 96 |
```bash
|
| 97 |
-
git clone https://github.com/
|
| 98 |
-
huggingface-cli download
|
| 99 |
cargo build --release
|
| 100 |
export ORT_DYLIB_PATH=/path/to/libonnxruntime.so # ARM64 build on the Pi
|
| 101 |
./target/release/step_4_inference --model-dir hf/onnx "c oi, e nho c qua"
|
|
@@ -107,7 +107,7 @@ The GitHub repo also has a Raspberry Pi Docker image with an HTTP endpoint (`POS
|
|
| 107 |
|
| 108 |
```bash
|
| 109 |
pip install onnxruntime tokenizers numpy huggingface_hub
|
| 110 |
-
huggingface-cli download
|
| 111 |
cd teencode-v3 && python inference_onnx.py "c oi, c muon hoi cai nay"
|
| 112 |
# chú ơi, cháu muốn hỏi cái này
|
| 113 |
```
|
|
|
|
| 3 |
- vi
|
| 4 |
license: mit
|
| 5 |
library_name: onnx
|
| 6 |
+
pipeline_tag: translation
|
| 7 |
tags:
|
| 8 |
+
- text2text-generation
|
| 9 |
+
- onnx
|
| 10 |
+
- vietnamese
|
| 11 |
+
- teencode
|
| 12 |
+
- text-normalization
|
| 13 |
+
- seq2seq
|
| 14 |
+
- int8
|
| 15 |
+
- raspberry-pi
|
| 16 |
model-index:
|
| 17 |
+
- name: TTS-standardlization
|
| 18 |
results:
|
| 19 |
- task:
|
| 20 |
type: text2text-generation
|
|
|
|
| 31 |
|
| 32 |
# teencode-normalizer v3
|
| 33 |
|
| 34 |
+
Encoder-decoder Transformer that rewrites Vietnamese **teencode** (abbreviations, missing tones, slang spellings, short pronouns) into standard Vietnamese. Small enough (~20.8 MB INT8) to run on a Raspberry Pi 4 with ONNX Runtime.
|
| 35 |
|
| 36 |
+
Code (Rust data prep / inference / HTTP server, Python training, Pi Docker, Colab): https://github.com/femboyvn/TFVN-TTS-standardlization
|
| 37 |
|
| 38 |
## Files
|
| 39 |
|
|
|
|
| 94 |
### Rust runner (recommended: beam 4 + guard)
|
| 95 |
|
| 96 |
```bash
|
| 97 |
+
git clone https://github.com/femboyvn/TFVN-TTS-standardlization && cd TFVN-TTS-standardlization
|
| 98 |
+
huggingface-cli download tfvn/TTS-standardlization --include "onnx/*" --local-dir hf
|
| 99 |
cargo build --release
|
| 100 |
export ORT_DYLIB_PATH=/path/to/libonnxruntime.so # ARM64 build on the Pi
|
| 101 |
./target/release/step_4_inference --model-dir hf/onnx "c oi, e nho c qua"
|
|
|
|
| 107 |
|
| 108 |
```bash
|
| 109 |
pip install onnxruntime tokenizers numpy huggingface_hub
|
| 110 |
+
huggingface-cli download tfvn/TTS-standardlization --local-dir teencode-v3
|
| 111 |
cd teencode-v3 && python inference_onnx.py "c oi, c muon hoi cai nay"
|
| 112 |
# chú ơi, cháu muốn hỏi cái này
|
| 113 |
```
|
onnx/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|