chiaseacc commited on
Commit
cb736b2
·
verified ·
1 Parent(s): c67e924

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +15 -15
  2. 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: text2text-generation
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: teencode-normalizer-v3
18
  results:
19
  - task:
20
  type: text2text-generation
@@ -31,9 +31,9 @@ model-index:
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/<you>/teencode-normalizer
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/<you>/teencode-normalizer && cd teencode-normalizer
98
- huggingface-cli download <user>/teencode-normalizer-v3 --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"
@@ -107,7 +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 <user>/teencode-normalizer-v3 --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
  ```
 
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