File size: 3,725 Bytes
bd94edd ec27144 bd94edd ec27144 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
---
license: apache-2.0
library_name: transformers.js
---
## Usage
### Python
```python
import os
import numpy as np
from onnxruntime import InferenceSession
# Tokens produced by phonemize() and tokenize() in kokoro.py
tokens = [50, 157, 43, 135, 16, 53, 135, 46, 16, 43, 102, 16, 56, 156, 57, 135, 6, 16, 102, 62, 61, 16, 70, 56, 16, 138, 56, 156, 72, 56, 61, 85, 123, 83, 44, 83, 54, 16, 53, 65, 156, 86, 61, 62, 131, 83, 56, 4, 16, 54, 156, 43, 102, 53, 16, 156, 72, 61, 53, 102, 112, 16, 70, 56, 16, 138, 56, 44, 156, 76, 158, 123, 56, 16, 62, 131, 156, 43, 102, 54, 46, 16, 102, 48, 16, 81, 47, 102, 54, 16, 54, 156, 51, 158, 46, 16, 70, 16, 92, 156, 135, 46, 16, 54, 156, 43, 102, 48, 4, 16, 81, 47, 102, 16, 50, 156, 72, 64, 83, 56, 62, 16, 156, 51, 158, 64, 83, 56, 16, 44, 157, 102, 56, 16, 44, 156, 76, 158, 123, 56, 4]
# Context length is 512, but leave room for the pad token 0 at the start & end
assert len(tokens) <= 510, len(tokens)
# Style vector based on len(tokens), ref_s has shape (1, 256)
voices = np.fromfile('./voices/af.bin', dtype=np.float32).reshape(-1, 1, 256)
ref_s = voices[len(tokens)]
# Add the pad ids, and reshape tokens, should now have shape (1, <=512)
tokens = [[0, *tokens, 0]]
model_name = 'model.onnx' # Options: model.onnx, model_fp16.onnx, model_quantized.onnx, model_q8f16.onnx, model_uint8.onnx, model_uint8f16.onnx, model_q4.onnx, model_q4f16.onnx
sess = InferenceSession(os.path.join('onnx', model_name))
audio = sess.run(None, dict(
input_ids=tokens,
style=ref_s,
speed=np.ones(1, dtype=np.float32),
))[0]
```
Optionally, save the audio to a file:
```
import scipy.io.wavfile as wavfile
wavfile.write('audio.wav', 24000, audio[0])
```
## Samples
| Model | Size (MB) | Sample |
|------------------------------------------------|-----------|-----------------------------------------------------------------------------------------------------------------------------------------|
| model.onnx (fp32) | 326 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2FnjexBuqPzfYUvWgs9eQ-_.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_fp16.onnx (fp16) | 163 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2F8Ebl44hMQonZs4MlykExt.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_quantized.onnx (8-bit) | 92.4 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2F9SLOt6ETclZ4yRdlJ0VIj.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_q8f16.onnx (Mixed precision) | 86 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2FgNDMqb33YEmYMbAIv_Grx.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_uint8.onnx (8-bit & mixed precision) | 177 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2FtpOWRHIWwEb0PJX46dCWQ.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_uint8f16.onnx (Mixed precision) | 114 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2FvtZhABzjP0pvGD7dRb5Vr.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_q4.onnx (4-bit matmul) | 305 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2F8FVn0IJIUfccEBWq8Fnw_.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> |
| model_q4f16.onnx (4-bit matmul & fp16 weights) | 154 | <audio controls src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F61b253b7ac5ecaae3d1efe0c%2F7DrgWC_1q00s-wUJuG44X.wav%26quot%3B%3C%2Fspan%3E%26gt%3B%3C%2Fspan%3E%3C%2Fspan%3E%3Cspan class="language-xml"></audio> | |