Ship the Rust engine: Python wheels, CLI, C library, WASM demo
Browse files- .gitattributes +9 -0
- README.md +57 -76
- eeh.pt → bin/linux-aarch64/eeh +2 -2
- onnx/model.onnx → bin/linux-x86_64/eeh +2 -2
- bin/macos-arm64/eeh +3 -0
- eeh-dict.bin +3 -0
- include/eeh.h +234 -0
- lib/linux-aarch64/libeeh_ffi.so +3 -0
- lib/linux-x86_64/libeeh_ffi.so +3 -0
- lib/macos-arm64/libeeh_ffi.dylib +3 -0
- onnx/config.json +0 -87
- python/eeh-0.1.0-py3-none-macosx_11_0_arm64.whl +3 -0
- python/eeh-0.1.0-py3-none-manylinux_2_28_aarch64.whl +3 -0
- python/eeh-0.1.0-py3-none-manylinux_2_28_x86_64.whl +3 -0
- samples/F1-hello.wav +2 -2
- samples/F1-numbers.wav +2 -2
- samples/F1-polite.wav +2 -2
- samples/F1-question.wav +2 -2
- samples/F1-story.wav +2 -2
- samples/M1-hello.wav +2 -2
- samples/M1-numbers.wav +2 -2
- samples/M1-polite.wav +2 -2
- samples/M1-question.wav +2 -2
- samples/M1-story.wav +2 -2
- tiny_voca/__init__.py +0 -10
- tiny_voca/config.py +0 -92
- tiny_voca/infer.py +0 -182
- tiny_voca/model.py +0 -379
- tiny_voca/text.py +0 -219
.gitattributes
CHANGED
|
@@ -44,3 +44,12 @@ samples/M1-numbers.wav filter=lfs diff=lfs merge=lfs -text
|
|
| 44 |
samples/M1-polite.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
samples/M1-question.wav filter=lfs diff=lfs merge=lfs -text
|
| 46 |
samples/M1-story.wav filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
samples/M1-polite.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
samples/M1-question.wav filter=lfs diff=lfs merge=lfs -text
|
| 46 |
samples/M1-story.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
bin/linux-aarch64/eeh filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
bin/linux-x86_64/eeh filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
bin/macos-arm64/eeh filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
lib/linux-aarch64/libeeh_ffi.so filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
lib/linux-x86_64/libeeh_ffi.so filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
lib/macos-arm64/libeeh_ffi.dylib filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
python/eeh-0.1.0-py3-none-macosx_11_0_arm64.whl filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
python/eeh-0.1.0-py3-none-manylinux_2_28_aarch64.whl filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
python/eeh-0.1.0-py3-none-manylinux_2_28_x86_64.whl filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -2,11 +2,12 @@
|
|
| 2 |
language: ja
|
| 3 |
license: apache-2.0
|
| 4 |
pipeline_tag: text-to-speech
|
| 5 |
-
library_name:
|
| 6 |
tags:
|
| 7 |
- text-to-speech
|
| 8 |
- japanese
|
| 9 |
-
-
|
|
|
|
| 10 |
- tiny
|
| 11 |
---
|
| 12 |
|
|
@@ -32,7 +33,7 @@ trained from scratch on 18.6 hours of speech by
|
|
| 32 |
| Voices | F1 (female, late 20s, calm and clear), M1 (male, early 30s, warm), Tokyo Japanese |
|
| 33 |
| Output | 24 kHz mono |
|
| 34 |
| Input | Japanese text (kanji, kana, numbers), read with OpenJTalk |
|
| 35 |
-
| Speed |
|
| 36 |
| Pretrained weights in the model | None |
|
| 37 |
| License | Apache-2.0 |
|
| 38 |
|
|
@@ -50,107 +51,87 @@ trained from scratch on 18.6 hours of speech by
|
|
| 50 |
|
| 51 |
| Path | Contents |
|
| 52 |
|---|---|
|
| 53 |
-
| `eeh.
|
| 54 |
-
| `eeh.
|
| 55 |
-
| `
|
| 56 |
-
| `
|
| 57 |
-
| `
|
|
|
|
| 58 |
| `samples/` | The audio on this page |
|
| 59 |
| `eval/report.json`, `eval/metrics.jsonl` | Evaluation report and the training log |
|
| 60 |
| `LICENSE` | Apache-2.0 |
|
| 61 |
|
| 62 |
## Usage
|
| 63 |
|
| 64 |
-
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
```bash
|
| 67 |
-
pip install torch numpy soundfile "pyopenjtalk>=0.4,<0.5"
|
| 68 |
hf download ctrltokyo/eeh-1 --local-dir eeh
|
| 69 |
cd eeh
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
--voice F1 \
|
| 74 |
-
--text "こんにちは。今日はいい天気ですね。" \
|
| 75 |
-
--output hello.wav
|
| 76 |
```
|
| 77 |
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
| `--text-file` | | Read the text from a UTF-8 file instead of `--text` |
|
| 81 |
-
| `--voice` | `F1` | `F1` or `M1` |
|
| 82 |
-
| `--speed` | 1.0 | Speaking rate |
|
| 83 |
-
| `--pitch-shift` | 0 | Added to log F0. 0.058 is about one semitone. |
|
| 84 |
-
| `--pitch-range` | 1.0 | Scales pitch movement around the utterance mean |
|
| 85 |
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
`tiny_voca.infer.speak_text` does the same.
|
| 91 |
|
| 92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
```bash
|
| 95 |
-
|
| 96 |
-
|
| 97 |
```
|
| 98 |
|
| 99 |
-
|
| 100 |
-
Rust and compiled to WebAssembly: a Japanese front end that reads text exactly
|
| 101 |
-
as OpenJTalk does (identical on more than 500,000 test texts), and the model.
|
| 102 |
-
It runs in a Web Worker and plays long text sentence by sentence as it is made;
|
| 103 |
-
the first sentence starts in under 0.1 s. The first visit downloads about 26 MB
|
| 104 |
-
(gzip): 17 MB of weights, 9 MB of dictionary and 0.4 MB of program, all kept by
|
| 105 |
-
the browser afterwards.
|
| 106 |
-
|
| 107 |
-
### ONNX
|
| 108 |
|
| 109 |
-
|
| 110 |
-
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
from tiny_voca.text import phonemize
|
| 117 |
-
|
| 118 |
-
phones = phonemize("こんにちは。")
|
| 119 |
-
one = lambda value: np.array([value], dtype=np.float32)
|
| 120 |
-
session = ort.InferenceSession("onnx/model.onnx")
|
| 121 |
-
audio, durations = session.run(None, {
|
| 122 |
-
"tokens": np.array([phones.ids], dtype=np.int64),
|
| 123 |
-
"stress": np.array([phones.stress], dtype=np.int64), # pitch-accent tone per token
|
| 124 |
-
"voice": np.array([0], dtype=np.int64), # 0 = F1, 1 = M1
|
| 125 |
-
"speed": one(1.0), "pitch_shift": one(0.0), "pitch_range": one(1.0),
|
| 126 |
-
})
|
| 127 |
-
audio = audio[0] * min(1.0, 0.99 / np.abs(audio[0]).max())
|
| 128 |
-
sf.write("hello.wav", audio, 24000)
|
| 129 |
-
```
|
| 130 |
|
| 131 |
-
|
| 132 |
-
|---|---|---|---|
|
| 133 |
-
| `tokens` | int64 | [1, N] | Symbol ids (`symbols` in `onnx/config.json`), with the start and end tokens |
|
| 134 |
-
| `stress` | int64 | [1, N] | Tokyo pitch-accent tone of the token's mora: 0 not a phone, 1 low, 2 high |
|
| 135 |
-
| `voice` | int64 | [1] | 0 = F1, 1 = M1 |
|
| 136 |
-
| `speed`, `pitch_shift`, `pitch_range` | float32 | [1] | As in the Python options |
|
| 137 |
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
| `durations` | int64 | [1, N] | Length of each token in frames of 256 samples |
|
| 142 |
|
| 143 |
-
|
|
|
|
|
|
|
|
|
|
| 144 |
|
| 145 |
## How it works
|
| 146 |
|
| 147 |
-
**Front end.**
|
| 148 |
-
Japanese Dictionary
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
eeh turns its labels into tokens:
|
| 152 |
|
| 153 |
-
- one token per
|
| 154 |
a long vowel is two tokens, one per mora;
|
| 155 |
- devoiced vowels (the u of です, the i of した) are their own tokens `A I U E O`;
|
| 156 |
- `<sp>` marks a boundary between accent phrases, and punctuation is kept;
|
|
|
|
| 2 |
language: ja
|
| 3 |
license: apache-2.0
|
| 4 |
pipeline_tag: text-to-speech
|
| 5 |
+
library_name: eeh
|
| 6 |
tags:
|
| 7 |
- text-to-speech
|
| 8 |
- japanese
|
| 9 |
+
- rust
|
| 10 |
+
- webassembly
|
| 11 |
- tiny
|
| 12 |
---
|
| 13 |
|
|
|
|
| 33 |
| Voices | F1 (female, late 20s, calm and clear), M1 (male, early 30s, warm), Tokyo Japanese |
|
| 34 |
| Output | 24 kHz mono |
|
| 35 |
| Input | Japanese text (kanji, kana, numbers), read with OpenJTalk |
|
| 36 |
+
| Speed | 120x real time on one CPU thread, 280x on four (Apple M4 Max); about 50x in a browser tab, first audio in under 0.1 s |
|
| 37 |
| Pretrained weights in the model | None |
|
| 38 |
| License | Apache-2.0 |
|
| 39 |
|
|
|
|
| 51 |
|
| 52 |
| Path | Contents |
|
| 53 |
|---|---|
|
| 54 |
+
| `eeh.safetensors` | Weights, float32 (18.2 MB) |
|
| 55 |
+
| `eeh-dict.bin` | The Japanese dictionary the front end reads (36 MB) |
|
| 56 |
+
| `python/` | Python wheels for macOS (arm64) and Linux (aarch64, x86_64) |
|
| 57 |
+
| `bin/<platform>/eeh` | Command-line program |
|
| 58 |
+
| `lib/<platform>/`, `include/eeh.h` | C library and header, for any language with a C FFI |
|
| 59 |
+
| `demo/` | The browser demo: the whole engine compiled to WebAssembly, the weights and the dictionary |
|
| 60 |
| `samples/` | The audio on this page |
|
| 61 |
| `eval/report.json`, `eval/metrics.jsonl` | Evaluation report and the training log |
|
| 62 |
| `LICENSE` | Apache-2.0 |
|
| 63 |
|
| 64 |
## Usage
|
| 65 |
|
| 66 |
+
eeh runs on its own engine, written in Rust: a Japanese front end that reads
|
| 67 |
+
text exactly as OpenJTalk does (identical on more than 500,000 test texts) and
|
| 68 |
+
the model. The same engine is behind the Python package, the command-line
|
| 69 |
+
program, the C library and the browser demo.
|
| 70 |
|
| 71 |
```bash
|
|
|
|
| 72 |
hf download ctrltokyo/eeh-1 --local-dir eeh
|
| 73 |
cd eeh
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
### Python
|
| 77 |
|
| 78 |
+
```bash
|
| 79 |
+
pip install python/eeh-0.1.0-py3-none-<your platform>.whl
|
|
|
|
|
|
|
|
|
|
| 80 |
```
|
| 81 |
|
| 82 |
+
```python
|
| 83 |
+
import eeh, soundfile
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
+
synth = eeh.Synthesizer("eeh.safetensors", "eeh-dict.bin")
|
| 86 |
+
audio = synth.speak("こんにちは。今日はいい天気ですね。", voice="F1") # float32 array, 24 kHz
|
| 87 |
+
soundfile.write("hello.wav", audio, synth.sample_rate)
|
| 88 |
+
```
|
|
|
|
| 89 |
|
| 90 |
+
`speak` takes `voice` (`F1` or `M1`), `speed` (1.0), `pitch_shift` (0; 0.058
|
| 91 |
+
is about one semitone), `pitch_range` (1.0) and `seed`. `speak_each(text,
|
| 92 |
+
callback)` hands over each sentence as soon as it is made, for streaming. The
|
| 93 |
+
package has no dependencies; it returns a NumPy array when NumPy is installed.
|
| 94 |
+
The synthesizer can be shared between threads.
|
| 95 |
+
|
| 96 |
+
### Command line
|
| 97 |
|
| 98 |
```bash
|
| 99 |
+
bin/macos-arm64/eeh speak --weights eeh.safetensors --dictionary eeh-dict.bin \
|
| 100 |
+
--voice M1 --text "こんにちは。今日はいい天気ですね。" --out hello.wav
|
| 101 |
```
|
| 102 |
|
| 103 |
+
### C and other languages
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
|
| 105 |
+
`lib/<platform>/libeeh_ffi` with `include/eeh.h`: `eeh_synthesizer_new` takes
|
| 106 |
+
the weights and dictionary as bytes, `eeh_speak` returns the audio and
|
| 107 |
+
`eeh_speak_each` streams it sentence by sentence. Errors come back as status
|
| 108 |
+
codes, never as crashes. Go, Node, Java, Ruby and Swift can call it through
|
| 109 |
+
their C FFI (all five are tested).
|
| 110 |
|
| 111 |
+
Text of any length works. It is split into sentences at 。!? and read one
|
| 112 |
+
sentence at a time; a quote followed by と or って stays with its sentence, and
|
| 113 |
+
a sentence too long for one call is cut after 、. A text without a final mark
|
| 114 |
+
gets 。. The audio never peaks above 0.99.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
|
| 116 |
+
### In a browser
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
+
```bash
|
| 119 |
+
python -m http.server --directory demo 8000
|
| 120 |
+
```
|
|
|
|
| 121 |
|
| 122 |
+
Then open `http://localhost:8000`. The engine runs in a Web Worker and plays
|
| 123 |
+
long text sentence by sentence as it is made. The first visit downloads about
|
| 124 |
+
26 MB (gzip): 17 MB of weights, 9 MB of dictionary and 0.4 MB of program, all
|
| 125 |
+
kept by the browser afterwards.
|
| 126 |
|
| 127 |
## How it works
|
| 128 |
|
| 129 |
+
**Front end.** eeh's own Rust front end reads the text the way OpenJTalk does
|
| 130 |
+
with the NAIST Japanese Dictionary: it splits it into words, picks each kanji's
|
| 131 |
+
reading, expands numbers, joins words into accent phrases and assigns their
|
| 132 |
+
accent types. It turns the result into tokens:
|
|
|
|
| 133 |
|
| 134 |
+
- one token per phoneme (`k`, `sh`, `a`, `N` for ん, `cl` for っ);
|
| 135 |
a long vowel is two tokens, one per mora;
|
| 136 |
- devoiced vowels (the u of です, the i of した) are their own tokens `A I U E O`;
|
| 137 |
- `<sp>` marks a boundary between accent phrases, and punctuation is kept;
|
eeh.pt → bin/linux-aarch64/eeh
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca00933dbcb98bf82f035a8e714fc842af077db191276f0c3c8ee16e98fcbec3
|
| 3 |
+
size 1837632
|
onnx/model.onnx → bin/linux-x86_64/eeh
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7d699136775ff59ea4c80cca0ded6398717b240d463d78e6c4a51ebf2dd7df
|
| 3 |
+
size 2629176
|
bin/macos-arm64/eeh
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98f6bb859181bdaec6d99886efb59ad07ec11f8a17562d67bcae01b6e9fb8881
|
| 3 |
+
size 1948768
|
eeh-dict.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d480c8806b230b113a37a28756748736b975c3aed37d5b27a3e8de7e32c6af
|
| 3 |
+
size 35927036
|
include/eeh.h
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/* eeh C API. Generated by cbindgen from rust/crates/eeh-ffi (generate-header.sh); do not edit. */
|
| 2 |
+
|
| 3 |
+
#ifndef EEH_H
|
| 4 |
+
#define EEH_H
|
| 5 |
+
|
| 6 |
+
#include <stdbool.h>
|
| 7 |
+
#include <stddef.h>
|
| 8 |
+
#include <stdint.h>
|
| 9 |
+
|
| 10 |
+
/**
|
| 11 |
+
* Result of a call. `EEH_STATUS_OK` is 0.
|
| 12 |
+
*/
|
| 13 |
+
typedef enum {
|
| 14 |
+
/**
|
| 15 |
+
* Success.
|
| 16 |
+
*/
|
| 17 |
+
EEH_STATUS_OK = 0,
|
| 18 |
+
/**
|
| 19 |
+
* A pointer was null or a string was not UTF-8.
|
| 20 |
+
*/
|
| 21 |
+
EEH_STATUS_INVALID_ARGUMENT = 1,
|
| 22 |
+
/**
|
| 23 |
+
* No sentence of the text could be read (eeh only reads Japanese for now).
|
| 24 |
+
*/
|
| 25 |
+
EEH_STATUS_NOTHING_TO_PRONOUNCE = 2,
|
| 26 |
+
/**
|
| 27 |
+
* The voice is not one of the model's.
|
| 28 |
+
*/
|
| 29 |
+
EEH_STATUS_UNKNOWN_VOICE = 3,
|
| 30 |
+
/**
|
| 31 |
+
* The dictionary is malformed, or the text could not be analysed.
|
| 32 |
+
*/
|
| 33 |
+
EEH_STATUS_FRONTEND = 4,
|
| 34 |
+
/**
|
| 35 |
+
* The weights are malformed or an option is out of range.
|
| 36 |
+
*/
|
| 37 |
+
EEH_STATUS_MODEL = 5,
|
| 38 |
+
/**
|
| 39 |
+
* Anything else, e.g. a word too long to speak or non-finite audio.
|
| 40 |
+
*/
|
| 41 |
+
EEH_STATUS_OTHER = 6,
|
| 42 |
+
/**
|
| 43 |
+
* An internal panic was caught; the call had no effect.
|
| 44 |
+
*/
|
| 45 |
+
EEH_STATUS_PANIC = 7,
|
| 46 |
+
} EehStatus;
|
| 47 |
+
|
| 48 |
+
/**
|
| 49 |
+
* An error: a code and a message. Opaque to C; read it with `eeh_error_code` and `eeh_error_message`.
|
| 50 |
+
*/
|
| 51 |
+
typedef struct EehError EehError;
|
| 52 |
+
|
| 53 |
+
/**
|
| 54 |
+
* A synthesizer and the voice names as C strings.
|
| 55 |
+
*/
|
| 56 |
+
typedef struct EehSynthesizer EehSynthesizer;
|
| 57 |
+
|
| 58 |
+
/**
|
| 59 |
+
* Options of a call; `NULL` for all defaults (see `eeh_options_default`).
|
| 60 |
+
*/
|
| 61 |
+
typedef struct {
|
| 62 |
+
/**
|
| 63 |
+
* Speaking rate, 0.25 to 4 (1 = as predicted, larger is faster).
|
| 64 |
+
*/
|
| 65 |
+
float speed;
|
| 66 |
+
/**
|
| 67 |
+
* Added to log F0 (0.058 is about one semitone).
|
| 68 |
+
*/
|
| 69 |
+
float pitch_shift;
|
| 70 |
+
/**
|
| 71 |
+
* Scales the pitch movement, 0 to 3 (1 = as predicted).
|
| 72 |
+
*/
|
| 73 |
+
float pitch_range;
|
| 74 |
+
/**
|
| 75 |
+
* Seed of the noise; sentence `i` uses `seed + i`.
|
| 76 |
+
*/
|
| 77 |
+
uint64_t seed;
|
| 78 |
+
/**
|
| 79 |
+
* The loudest sample of the audio: louder audio is scaled down to it. Zero or less (or NaN) leaves
|
| 80 |
+
* the model's output as it is. In `eeh_speak_each` each sentence is limited on its own.
|
| 81 |
+
*/
|
| 82 |
+
float peak;
|
| 83 |
+
} EehOptions;
|
| 84 |
+
|
| 85 |
+
/**
|
| 86 |
+
* Called by `eeh_speak_each` for each sentence: its text (NUL-terminated UTF-8) and `len` samples at
|
| 87 |
+
* `audio`, both valid only during the call. Return `false` to stop.
|
| 88 |
+
*/
|
| 89 |
+
typedef bool (*EehUtteranceCallback)(const char *text,
|
| 90 |
+
const float *audio,
|
| 91 |
+
size_t len,
|
| 92 |
+
void *user_data);
|
| 93 |
+
|
| 94 |
+
#ifdef __cplusplus
|
| 95 |
+
extern "C" {
|
| 96 |
+
#endif // __cplusplus
|
| 97 |
+
|
| 98 |
+
/**
|
| 99 |
+
* The version of the library, e.g. `"0.1.0"`. Static; never freed.
|
| 100 |
+
*/
|
| 101 |
+
const char *eeh_version(void);
|
| 102 |
+
|
| 103 |
+
/**
|
| 104 |
+
* Writes the default options (speed 1, no pitch change, seed 0, peak 0.99) to `*options`.
|
| 105 |
+
*
|
| 106 |
+
* # Safety
|
| 107 |
+
* `options` is null or points to writable memory for an `EehOptions`.
|
| 108 |
+
*/
|
| 109 |
+
void eeh_options_default(EehOptions *options);
|
| 110 |
+
|
| 111 |
+
/**
|
| 112 |
+
* Loads a synthesizer from the bytes of the weights file (safetensors) and of the packed dictionary
|
| 113 |
+
* (both are copied or parsed during the call; the buffers may be freed afterwards).
|
| 114 |
+
*
|
| 115 |
+
* Returns `NULL` on failure, with `*err` set when `err` is not `NULL`. Free the result with
|
| 116 |
+
* `eeh_synthesizer_free` and the error with `eeh_error_free`. A synthesizer can be used from
|
| 117 |
+
* several threads at once.
|
| 118 |
+
*
|
| 119 |
+
* # Safety
|
| 120 |
+
* Each buffer is `NULL` or has that many readable bytes; `err` is `NULL` or points to a writable `EehError*`.
|
| 121 |
+
*/
|
| 122 |
+
EehSynthesizer *eeh_synthesizer_new(const uint8_t *weights,
|
| 123 |
+
size_t weights_len,
|
| 124 |
+
const uint8_t *dictionary,
|
| 125 |
+
size_t dictionary_len,
|
| 126 |
+
EehError **err);
|
| 127 |
+
|
| 128 |
+
/**
|
| 129 |
+
* Frees a synthesizer. `NULL` is fine. No other call may use it at the same time or after.
|
| 130 |
+
*
|
| 131 |
+
* # Safety
|
| 132 |
+
* `synth` is `NULL` or came from `eeh_synthesizer_new` and is not freed twice.
|
| 133 |
+
*/
|
| 134 |
+
void eeh_synthesizer_free(EehSynthesizer *synth);
|
| 135 |
+
|
| 136 |
+
/**
|
| 137 |
+
* Sample rate of the audio in Hz; 0 when `synth` is `NULL`.
|
| 138 |
+
*
|
| 139 |
+
* # Safety
|
| 140 |
+
* `synth` is `NULL` or a live synthesizer.
|
| 141 |
+
*/
|
| 142 |
+
uint32_t eeh_sample_rate(const EehSynthesizer *synth);
|
| 143 |
+
|
| 144 |
+
/**
|
| 145 |
+
* Number of voices of the model; 0 when `synth` is `NULL`.
|
| 146 |
+
*
|
| 147 |
+
* # Safety
|
| 148 |
+
* `synth` is `NULL` or a live synthesizer.
|
| 149 |
+
*/
|
| 150 |
+
size_t eeh_voice_count(const EehSynthesizer *synth);
|
| 151 |
+
|
| 152 |
+
/**
|
| 153 |
+
* Name of voice `index` (e.g. `"F1"`), valid until the synthesizer is freed; `NULL` when out of range.
|
| 154 |
+
*
|
| 155 |
+
* # Safety
|
| 156 |
+
* `synth` is `NULL` or a live synthesizer.
|
| 157 |
+
*/
|
| 158 |
+
const char *eeh_voice_name(const EehSynthesizer *synth,
|
| 159 |
+
size_t index);
|
| 160 |
+
|
| 161 |
+
/**
|
| 162 |
+
* Speaks `utf8` (NUL-terminated) in `voice` and returns all the audio.
|
| 163 |
+
*
|
| 164 |
+
* On success `*audio` points to `*len` samples (mono, `eeh_sample_rate` Hz, `float`) that the caller frees with `eeh_audio_free(*audio, *len)`.
|
| 165 |
+
* `options` may be `NULL`. Returns `EEH_STATUS_OK` or an error code, with `*err` set when `err` is not
|
| 166 |
+
* `NULL` (free it with `eeh_error_free`); `*audio` is `NULL` and `*len` 0 on failure.
|
| 167 |
+
*
|
| 168 |
+
* # Safety
|
| 169 |
+
* `synth` is live; `utf8` and `voice` are NUL-terminated strings; `options` is `NULL` or readable;
|
| 170 |
+
* `audio` and `len` are writable; `err` is `NULL` or points to a writable `EehError*`.
|
| 171 |
+
*/
|
| 172 |
+
EehStatus eeh_speak(const EehSynthesizer *synth,
|
| 173 |
+
const char *utf8,
|
| 174 |
+
const char *voice,
|
| 175 |
+
const EehOptions *options,
|
| 176 |
+
float **audio,
|
| 177 |
+
size_t *len,
|
| 178 |
+
EehError **err);
|
| 179 |
+
|
| 180 |
+
/**
|
| 181 |
+
* Like `eeh_speak`, but hands each sentence to `callback` as soon as it is made (streaming).
|
| 182 |
+
*
|
| 183 |
+
* The audio is only valid during the callback. The callback returns `false` to stop early (the result is then
|
| 184 |
+
* still `EEH_STATUS_OK`). It runs on the calling thread and must not call back into the same
|
| 185 |
+
* synthesizer's `eeh_synthesizer_free`.
|
| 186 |
+
*
|
| 187 |
+
* # Safety
|
| 188 |
+
* As `eeh_speak`; `callback` is a valid function and `user_data` whatever it expects.
|
| 189 |
+
*/
|
| 190 |
+
EehStatus eeh_speak_each(const EehSynthesizer *synth,
|
| 191 |
+
const char *utf8,
|
| 192 |
+
const char *voice,
|
| 193 |
+
const EehOptions *options,
|
| 194 |
+
EehUtteranceCallback callback,
|
| 195 |
+
void *user_data,
|
| 196 |
+
EehError **err);
|
| 197 |
+
|
| 198 |
+
/**
|
| 199 |
+
* Frees audio from `eeh_speak`; `len` is the length it returned. `NULL` is fine.
|
| 200 |
+
*
|
| 201 |
+
* # Safety
|
| 202 |
+
* `audio` is `NULL` or the pointer and `len` the length `eeh_speak` returned, not freed twice.
|
| 203 |
+
*/
|
| 204 |
+
void eeh_audio_free(float *audio, size_t len);
|
| 205 |
+
|
| 206 |
+
/**
|
| 207 |
+
* The message of an error (NUL-terminated UTF-8), valid until `eeh_error_free`; `""` for `NULL`.
|
| 208 |
+
*
|
| 209 |
+
* # Safety
|
| 210 |
+
* `error` is `NULL` or a live error.
|
| 211 |
+
*/
|
| 212 |
+
const char *eeh_error_message(const EehError *error);
|
| 213 |
+
|
| 214 |
+
/**
|
| 215 |
+
* The status code of an error; `EEH_STATUS_INVALID_ARGUMENT` for `NULL`.
|
| 216 |
+
*
|
| 217 |
+
* # Safety
|
| 218 |
+
* `error` is `NULL` or a live error.
|
| 219 |
+
*/
|
| 220 |
+
EehStatus eeh_error_code(const EehError *error);
|
| 221 |
+
|
| 222 |
+
/**
|
| 223 |
+
* Frees an error. `NULL` is fine.
|
| 224 |
+
*
|
| 225 |
+
* # Safety
|
| 226 |
+
* `error` is `NULL` or came from this library and is not freed twice.
|
| 227 |
+
*/
|
| 228 |
+
void eeh_error_free(EehError *error);
|
| 229 |
+
|
| 230 |
+
#ifdef __cplusplus
|
| 231 |
+
} // extern "C"
|
| 232 |
+
#endif // __cplusplus
|
| 233 |
+
|
| 234 |
+
#endif /* EEH_H */
|
lib/linux-aarch64/libeeh_ffi.so
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:329deb93b91717ba4d689e546cd8fe9f1601a446aaf6664fa7db5c22fb7f0755
|
| 3 |
+
size 1697712
|
lib/linux-x86_64/libeeh_ffi.so
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a88022fe31aa91b65a6c1353ca7c67e392e664ba8f9b1b175407e001d2fed8a1
|
| 3 |
+
size 2451936
|
lib/macos-arm64/libeeh_ffi.dylib
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5792dfd365078178419e8b0fa7f48f8e7da68acf4edde5f67d09072b88e97dc
|
| 3 |
+
size 1887136
|
onnx/config.json
DELETED
|
@@ -1,87 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"sample_rate": 24000,
|
| 3 |
-
"hop": 256,
|
| 4 |
-
"voices": [
|
| 5 |
-
"F1",
|
| 6 |
-
"M1"
|
| 7 |
-
],
|
| 8 |
-
"symbols": [
|
| 9 |
-
"<pad>",
|
| 10 |
-
"<bos>",
|
| 11 |
-
"<eos>",
|
| 12 |
-
"<sp>",
|
| 13 |
-
"<unk>",
|
| 14 |
-
",",
|
| 15 |
-
".",
|
| 16 |
-
"?",
|
| 17 |
-
"!",
|
| 18 |
-
";",
|
| 19 |
-
":",
|
| 20 |
-
"\"",
|
| 21 |
-
"(",
|
| 22 |
-
")",
|
| 23 |
-
"—",
|
| 24 |
-
"…",
|
| 25 |
-
"k",
|
| 26 |
-
"ky",
|
| 27 |
-
"kw",
|
| 28 |
-
"g",
|
| 29 |
-
"gy",
|
| 30 |
-
"gw",
|
| 31 |
-
"s",
|
| 32 |
-
"sh",
|
| 33 |
-
"z",
|
| 34 |
-
"j",
|
| 35 |
-
"t",
|
| 36 |
-
"ty",
|
| 37 |
-
"ch",
|
| 38 |
-
"ts",
|
| 39 |
-
"d",
|
| 40 |
-
"dy",
|
| 41 |
-
"n",
|
| 42 |
-
"ny",
|
| 43 |
-
"h",
|
| 44 |
-
"hy",
|
| 45 |
-
"f",
|
| 46 |
-
"b",
|
| 47 |
-
"by",
|
| 48 |
-
"p",
|
| 49 |
-
"py",
|
| 50 |
-
"m",
|
| 51 |
-
"my",
|
| 52 |
-
"y",
|
| 53 |
-
"r",
|
| 54 |
-
"ry",
|
| 55 |
-
"w",
|
| 56 |
-
"v",
|
| 57 |
-
"N",
|
| 58 |
-
"cl",
|
| 59 |
-
"a",
|
| 60 |
-
"i",
|
| 61 |
-
"u",
|
| 62 |
-
"e",
|
| 63 |
-
"o",
|
| 64 |
-
"A",
|
| 65 |
-
"I",
|
| 66 |
-
"U",
|
| 67 |
-
"E",
|
| 68 |
-
"O"
|
| 69 |
-
],
|
| 70 |
-
"max_tokens": 512,
|
| 71 |
-
"max_frames": 3000,
|
| 72 |
-
"step": 104000,
|
| 73 |
-
"frontend": "pyopenjtalk",
|
| 74 |
-
"frontend_fingerprint": "785d412fa394ae31d619203871d1b134404e24241c324cab897dddc1d22c8f77",
|
| 75 |
-
"inputs": [
|
| 76 |
-
"tokens",
|
| 77 |
-
"stress",
|
| 78 |
-
"voice",
|
| 79 |
-
"speed",
|
| 80 |
-
"pitch_shift",
|
| 81 |
-
"pitch_range"
|
| 82 |
-
],
|
| 83 |
-
"outputs": [
|
| 84 |
-
"audio",
|
| 85 |
-
"durations"
|
| 86 |
-
]
|
| 87 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
python/eeh-0.1.0-py3-none-macosx_11_0_arm64.whl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d646c44f04df32f14c2d1fd0f2adf68d507af6858ccdcca7cdd107fa099927d
|
| 3 |
+
size 790568
|
python/eeh-0.1.0-py3-none-manylinux_2_28_aarch64.whl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc08a406214f7711b5cb006e91d1dff2307fb9e5103e2dd7be7fcd68eb884ec7
|
| 3 |
+
size 786552
|
python/eeh-0.1.0-py3-none-manylinux_2_28_x86_64.whl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72b5bd3cd18c7100976b476120dc96e4070de41d8a59ebfc5ce8bec664dd8976
|
| 3 |
+
size 1051341
|
samples/F1-hello.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73af3fd1b0f0f2d7e58411c99af48ac4ba029dd2863371dcd85eefc7932f2bd1
|
| 3 |
+
size 668716
|
samples/F1-numbers.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffaf2dc813a0feabb92ccaa7a8d082aa1307c675be3c808a73c4062a6f48533
|
| 3 |
+
size 663596
|
samples/F1-polite.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba5c9fae74cbc4f7ee51a06da2cfd8ad28b17a04b6ef8035c4def4b9d53cc4df
|
| 3 |
+
size 553004
|
samples/F1-question.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ac158892770577ec6560f6262aba6d0012f340a0513b0a9580e596f2845daa2
|
| 3 |
+
size 404524
|
samples/F1-story.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b64c92f6790227d8ffe66ca0f9973cd2a52612a5d4131e3a4fc8bcbb6a0f16
|
| 3 |
+
size 750636
|
samples/M1-hello.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b66e92cfe711b5be2180fea913a1d34ae0f4ba7c5e06a2645ca259020ed14a36
|
| 3 |
+
size 646188
|
samples/M1-numbers.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecd845b33e263655a29e3593ecdd683d05ed35f2510831534744674b41ed1cf7
|
| 3 |
+
size 649260
|
samples/M1-polite.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e7bf8399833a29c6059e427beef465ec235ca48f62e436393dcc5b10668c68b
|
| 3 |
+
size 543788
|
samples/M1-question.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ece4db5aaf0c242c76897fa53e6c6d1231005bee3b738ea900a5ae426a052faa
|
| 3 |
+
size 395308
|
samples/M1-story.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa9b91a4ac2da5a930aaa71c2c7ce00fb5c22c37bb2fbf1025a245f9b64c930
|
| 3 |
+
size 708652
|
tiny_voca/__init__.py
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 1 |
-
"""tiny-voca: a small two-voice TTS trained from scratch.
|
| 2 |
-
|
| 3 |
-
The speech model loads no pretrained weights. A pretrained phoneme recogniser
|
| 4 |
-
is used only by the annotation step, and an ASR model only by evaluation.
|
| 5 |
-
"""
|
| 6 |
-
|
| 7 |
-
from .config import Config
|
| 8 |
-
from .model import TinyVoca
|
| 9 |
-
|
| 10 |
-
__all__ = ["Config", "TinyVoca"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tiny_voca/config.py
DELETED
|
@@ -1,92 +0,0 @@
|
|
| 1 |
-
from dataclasses import asdict, dataclass
|
| 2 |
-
import hashlib
|
| 3 |
-
import json
|
| 4 |
-
|
| 5 |
-
CHECKPOINT_FORMAT = 4 # 2-3: byte tokens + learned aligner (rejected explicitly).
|
| 6 |
-
ANNOTATION_VERSION = 3
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
def _digest(value):
|
| 10 |
-
return hashlib.sha256(json.dumps(value, sort_keys=True).encode()).hexdigest()
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
@dataclass(frozen=True)
|
| 14 |
-
class Config:
|
| 15 |
-
# Acoustic features (unchanged since feature schema 2; existing files are reused).
|
| 16 |
-
sample_rate: int = 24000
|
| 17 |
-
hop: int = 256
|
| 18 |
-
n_fft: int = 1024
|
| 19 |
-
n_mels: int = 80
|
| 20 |
-
f0_min: float = 50.0
|
| 21 |
-
f0_max: float = 600.0
|
| 22 |
-
speakers: tuple[str, ...] = ("F1", "M1")
|
| 23 |
-
# Phoneme tokens from tiny_voca.text.SYMBOLS (Japanese front end, version 1).
|
| 24 |
-
vocab_size: int = 60
|
| 25 |
-
# Text encoder and frame-level transformer.
|
| 26 |
-
channels: int = 192
|
| 27 |
-
heads: int = 4
|
| 28 |
-
feedforward: int = 640
|
| 29 |
-
kernel: int = 7
|
| 30 |
-
encoder_layers: int = 4
|
| 31 |
-
prosody_layers: int = 2
|
| 32 |
-
acoustic_layers: int = 5
|
| 33 |
-
dropout: float = 0.1
|
| 34 |
-
predictor_channels: int = 128
|
| 35 |
-
# Source-filter waveform head: harmonic branch and noise branch STFT sizes,
|
| 36 |
-
# causal/anticausal complex-cepstrum orders.
|
| 37 |
-
synth_fft: int = 512
|
| 38 |
-
synth_hop: int = 128
|
| 39 |
-
noise_fft: int = 256
|
| 40 |
-
noise_hop: int = 64
|
| 41 |
-
cep_causal: int = 80
|
| 42 |
-
cep_anti: int = 16
|
| 43 |
-
noise_cep: int = 32
|
| 44 |
-
harmonic_limit: float = 0.47
|
| 45 |
-
max_tokens: int = 512
|
| 46 |
-
max_frames: int = 3000
|
| 47 |
-
mel_mean: float = -5.0
|
| 48 |
-
mel_scale: float = 5.0
|
| 49 |
-
energy_mean: float = -4.0
|
| 50 |
-
energy_scale: float = 2.0
|
| 51 |
-
pitch_reference_hz: float = 200.0
|
| 52 |
-
|
| 53 |
-
def __post_init__(self):
|
| 54 |
-
from .text import SYMBOLS
|
| 55 |
-
if self.vocab_size != len(SYMBOLS):
|
| 56 |
-
raise ValueError(f"vocab_size must equal the phoneme inventory size {len(SYMBOLS)}")
|
| 57 |
-
if self.channels % self.heads or (self.channels // self.heads) % 2:
|
| 58 |
-
raise ValueError("channels must be divisible by heads with an even head width")
|
| 59 |
-
if not self.speakers or len(set(self.speakers)) != len(self.speakers):
|
| 60 |
-
raise ValueError("speaker names must be unique and nonempty")
|
| 61 |
-
for fft, hop in ((self.synth_fft, self.synth_hop), (self.noise_fft, self.noise_hop)):
|
| 62 |
-
if fft != 4 * hop or self.hop % hop:
|
| 63 |
-
raise ValueError("synthesis windows need 4x overlap and a hop dividing the acoustic hop")
|
| 64 |
-
if self.cep_causal + self.cep_anti >= self.synth_fft // 2 or self.noise_cep >= self.noise_fft // 2:
|
| 65 |
-
raise ValueError("cepstrum orders must be well below half the synthesis FFT size")
|
| 66 |
-
if min(self.encoder_layers, self.prosody_layers, self.acoustic_layers, self.kernel) < 1 or not self.kernel % 2:
|
| 67 |
-
raise ValueError("layer counts must be positive and the kernel odd")
|
| 68 |
-
if min(self.mel_scale, self.energy_scale) <= 0 or not 0 < self.harmonic_limit < 0.5:
|
| 69 |
-
raise ValueError("invalid normalization scale or harmonic limit")
|
| 70 |
-
|
| 71 |
-
def to_dict(self):
|
| 72 |
-
return asdict(self)
|
| 73 |
-
|
| 74 |
-
@classmethod
|
| 75 |
-
def from_dict(cls, value):
|
| 76 |
-
return cls(**{**value, "speakers": tuple(value["speakers"])})
|
| 77 |
-
|
| 78 |
-
@property
|
| 79 |
-
def fingerprint(self):
|
| 80 |
-
return _digest(self.to_dict())
|
| 81 |
-
|
| 82 |
-
@property
|
| 83 |
-
def acoustic_config(self):
|
| 84 |
-
"""Settings that determine stored wave/mel/prosody tensors. Tokens and
|
| 85 |
-
durations are versioned separately by the annotation layer."""
|
| 86 |
-
fields = ("sample_rate", "hop", "n_fft", "n_mels", "f0_min", "f0_max")
|
| 87 |
-
return {**{key: getattr(self, key) for key in fields}, "feature_version": 2,
|
| 88 |
-
"pitch_reference_hz": 200, "log_floor": 1e-5}
|
| 89 |
-
|
| 90 |
-
@property
|
| 91 |
-
def acoustic_fingerprint(self):
|
| 92 |
-
return _digest(self.acoustic_config)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tiny_voca/infer.py
DELETED
|
@@ -1,182 +0,0 @@
|
|
| 1 |
-
import argparse
|
| 2 |
-
from pathlib import Path
|
| 3 |
-
import re
|
| 4 |
-
import torch
|
| 5 |
-
from .config import CHECKPOINT_FORMAT, Config
|
| 6 |
-
from .model import TinyVoca, UtteranceTooLong
|
| 7 |
-
from .text import NothingToPronounce, frontend_fingerprint, phonemize
|
| 8 |
-
|
| 9 |
-
# The loudest sample of the audio that ``speak_text`` and the command return.
|
| 10 |
-
PEAK = 0.99
|
| 11 |
-
# Said when no sentence of a text could be read. The browser demo says the same.
|
| 12 |
-
JAPANESE_ONLY = "eeh only reads Japanese for now"
|
| 13 |
-
_SPACE = re.compile("[\\s" + chr(0xFEFF) + "]+") # JavaScript's \s, which the demo uses, takes U+FEFF too
|
| 14 |
-
# A sentence ends at 。!?… (full or half width) and at a full stop that is not
|
| 15 |
-
# a decimal point; closing quotes and brackets after the mark stay with it. A
|
| 16 |
-
# quotation that goes on with と or って (「行こう。」と言った) is not an end.
|
| 17 |
-
_END_MARKS = "。.!?!?…"
|
| 18 |
-
_CLOSING = "」』))\"'”’】»"
|
| 19 |
-
_END = rf"(?:(?:[{_END_MARKS}]|(?<!\d)\.|\.(?!\d))(?![{_END_MARKS}.]*[{_CLOSING}]+[とっ]))"
|
| 20 |
-
_SENTENCE = re.compile(rf"(?:(?!{_END}).)+(?:{_END})*[{_CLOSING}]*|(?:{_END})+[{_CLOSING}]*", re.S)
|
| 21 |
-
_MARKED = frozenset(_END_MARKS + "、,;:;:.")
|
| 22 |
-
_CLAUSE_END = re.compile(r"(?<=[、,;:;:—])")
|
| 23 |
-
_TEXT_END = re.compile("[\\s" + chr(0xFEFF) + "]+$")
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
def load_model(path, device="cpu"):
|
| 27 |
-
state = torch.load(path, map_location="cpu", weights_only=True)
|
| 28 |
-
if state.get("format_version") != CHECKPOINT_FORMAT:
|
| 29 |
-
raise ValueError("unsupported checkpoint format: byte-token checkpoints (format 2-3) cannot be used with this code")
|
| 30 |
-
if state["frontend"]["fingerprint"] != frontend_fingerprint():
|
| 31 |
-
raise ValueError("checkpoint was trained with a different phoneme inventory/front end")
|
| 32 |
-
model = TinyVoca(Config.from_dict(state["config"]))
|
| 33 |
-
model.load_state_dict(state["model"], strict=True)
|
| 34 |
-
return model.to(device).eval()
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
def sentences(text):
|
| 38 |
-
"""The sentences of ``text``, never cut inside a number. The browser demo
|
| 39 |
-
splits the same way (``web/public/worker.js``); keep the two alike."""
|
| 40 |
-
parts = (part.strip() for part in _SENTENCE.findall(_SPACE.sub(" ", text).strip()))
|
| 41 |
-
return [part for part in parts if any(char.isalnum() for char in part)]
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
def finished(text):
|
| 45 |
-
"""``text`` with 。 added when it ends without a mark. Before a final mark
|
| 46 |
-
the voice lets the last mora fall; without one the audio breaks off. A
|
| 47 |
-
closing quote or bracket after the mark is fine; an emoji or a sign is no
|
| 48 |
-
mark. The browser demo does the same (``web/public/worker.js``); keep the
|
| 49 |
-
two alike."""
|
| 50 |
-
body = _TEXT_END.sub("", text)
|
| 51 |
-
if not body:
|
| 52 |
-
return text
|
| 53 |
-
core = body.rstrip(_CLOSING)
|
| 54 |
-
return text if core and core[-1] in _MARKED else body + "。"
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
def shorter(text):
|
| 58 |
-
"""``text`` in smaller pieces: cut after 、 and the like if it has any,
|
| 59 |
-
else in two halves, never inside a number. ``[]`` for a single character."""
|
| 60 |
-
pieces = [piece for piece in _CLAUSE_END.split(text) if piece.strip()]
|
| 61 |
-
if len(pieces) > 1:
|
| 62 |
-
return pieces
|
| 63 |
-
if len(text) < 2:
|
| 64 |
-
return []
|
| 65 |
-
cuts = [i for i in range(1, len(text)) if not (text[i - 1].isdigit() and text[i].isdigit())]
|
| 66 |
-
if not cuts:
|
| 67 |
-
return []
|
| 68 |
-
middle = min(cuts, key=lambda i: abs(i - len(text) / 2))
|
| 69 |
-
return [text[:middle], text[middle:]]
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
def limit_peak(wave, peak=PEAK):
|
| 73 |
-
"""``wave`` scaled down as a whole when its loudest sample is above
|
| 74 |
-
``peak``; quieter audio is returned as it is. The model sometimes peaks
|
| 75 |
-
above 1.0, and that clips when the audio is saved as 16-bit samples."""
|
| 76 |
-
loudest = float(wave.abs().max()) if wave.numel() else 0.0
|
| 77 |
-
return wave * (peak / loudest) if loudest > peak else wave
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
def _voice(model, phones, voice, speed, pitch_shift, seed, pitch_range):
|
| 81 |
-
"""Phonemes -> (float waveform tensor, details): one call of the model."""
|
| 82 |
-
device = next(model.parameters()).device
|
| 83 |
-
tokens = torch.tensor([phones.ids], device=device)
|
| 84 |
-
stress = torch.tensor([phones.stress], device=device)
|
| 85 |
-
speaker = torch.tensor([model.config.speakers.index(voice)], device=device)
|
| 86 |
-
audio, lengths, details = model.synthesize(tokens, stress, torch.tensor([len(phones)], device=device), speaker, speed, pitch_shift, seed, pitch_range)
|
| 87 |
-
if not torch.isfinite(audio).all():
|
| 88 |
-
raise RuntimeError("model produced non-finite audio")
|
| 89 |
-
return audio[0, :int(lengths[0])].cpu(), details
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
def speak(model, text, voice, speed=1.0, pitch_shift=0.0, seed=0, pitch_range=1.0):
|
| 93 |
-
"""One utterance: text -> (float waveform tensor, phonemized text, details).
|
| 94 |
-
Same front end as training. The audio is the model's output as it is and
|
| 95 |
-
can peak above 1.0 (see ``limit_peak``). ``speak_text`` reads text of any
|
| 96 |
-
length."""
|
| 97 |
-
phones = phonemize(text)
|
| 98 |
-
if len(phones) > model.config.max_tokens:
|
| 99 |
-
raise ValueError("text is too long for one utterance; speak_text splits it into sentences")
|
| 100 |
-
wave, details = _voice(model, phones, voice, speed, pitch_shift, seed, pitch_range)
|
| 101 |
-
return wave, phones, details
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
def speak_text(model, text, voice, speed=1.0, pitch_shift=0.0, seed=0, pitch_range=1.0, peak=PEAK):
|
| 105 |
-
"""Text of any length -> (float waveform tensor, phonemized utterances).
|
| 106 |
-
|
| 107 |
-
The text is read sentence by sentence and the audio is joined. A text that
|
| 108 |
-
ends without a mark gets a full stop (``finished``). A sentence
|
| 109 |
-
too long for one call of the model (``max_tokens`` phonemes or
|
| 110 |
-
``max_frames`` frames) is cut after commas, then between words. A sentence
|
| 111 |
-
with nothing to pronounce (another script, a face, signs only) is skipped;
|
| 112 |
-
when no sentence could be read, ``NothingToPronounce`` says so. The audio
|
| 113 |
-
is scaled down as a whole when it peaks above ``peak``, so that it can be
|
| 114 |
-
saved as 16-bit samples without clipping; ``peak=None`` returns the
|
| 115 |
-
model's output as it is."""
|
| 116 |
-
limit = model.config.max_tokens - 12
|
| 117 |
-
waves, spoken = [], []
|
| 118 |
-
|
| 119 |
-
def read(piece):
|
| 120 |
-
try:
|
| 121 |
-
phones = phonemize(piece)
|
| 122 |
-
except NothingToPronounce:
|
| 123 |
-
return
|
| 124 |
-
if len(phones) <= limit:
|
| 125 |
-
try:
|
| 126 |
-
wave, _ = _voice(model, phones, voice, speed, pitch_shift, seed + len(waves), pitch_range)
|
| 127 |
-
except UtteranceTooLong:
|
| 128 |
-
pass
|
| 129 |
-
else:
|
| 130 |
-
waves.append(wave)
|
| 131 |
-
spoken.append(phones)
|
| 132 |
-
return
|
| 133 |
-
pieces = shorter(piece)
|
| 134 |
-
if not pieces:
|
| 135 |
-
raise ValueError(f"one word is too long to speak: {piece[:40]!r}")
|
| 136 |
-
for part in pieces:
|
| 137 |
-
read(part)
|
| 138 |
-
|
| 139 |
-
for sentence in sentences(finished(text)):
|
| 140 |
-
read(sentence)
|
| 141 |
-
if not waves:
|
| 142 |
-
raise NothingToPronounce(f"nothing in the text could be read: {JAPANESE_ONLY}")
|
| 143 |
-
wave = torch.cat(waves)
|
| 144 |
-
return (wave if peak is None else limit_peak(wave, peak)), spoken
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
def main():
|
| 148 |
-
parser = argparse.ArgumentParser(description="Generate speech from a trained tiny-voca inference checkpoint")
|
| 149 |
-
parser.add_argument("--checkpoint", type=Path, required=True)
|
| 150 |
-
source = parser.add_mutually_exclusive_group(required=True)
|
| 151 |
-
source.add_argument("--text", help="Text of any length; it is read sentence by sentence")
|
| 152 |
-
source.add_argument("--text-file", type=Path, help="Read the text from a file (UTF-8)")
|
| 153 |
-
parser.add_argument("--voice", help="A voice of the checkpoint (default: its first, e.g. F1)")
|
| 154 |
-
parser.add_argument("--output", type=Path, required=True)
|
| 155 |
-
parser.add_argument("--speed", type=float, default=1)
|
| 156 |
-
parser.add_argument("--pitch-shift", type=float, default=0, help="Added to log F0 (0.058 is about one semitone)")
|
| 157 |
-
parser.add_argument("--pitch-range", type=float, default=1, help="Scale pitch movement around the utterance mean (1 = as predicted)")
|
| 158 |
-
parser.add_argument("--device", default="cpu")
|
| 159 |
-
args = parser.parse_args()
|
| 160 |
-
import soundfile as sf
|
| 161 |
-
model = load_model(args.checkpoint, args.device)
|
| 162 |
-
voice = args.voice or model.config.speakers[0]
|
| 163 |
-
if voice not in model.config.speakers:
|
| 164 |
-
parser.error(f"--voice must be one of {', '.join(model.config.speakers)}")
|
| 165 |
-
text = args.text if args.text is not None else args.text_file.read_text(encoding="utf-8")
|
| 166 |
-
try:
|
| 167 |
-
raw, spoken = speak_text(model, text, voice, args.speed, args.pitch_shift, pitch_range=args.pitch_range, peak=None)
|
| 168 |
-
except NothingToPronounce:
|
| 169 |
-
parser.exit(1, f"{JAPANESE_ONLY}. Nothing in the text could be read, so no file was written.\n")
|
| 170 |
-
wave = limit_peak(raw)
|
| 171 |
-
args.output.parent.mkdir(parents=True, exist_ok=True)
|
| 172 |
-
# Float samples, never above PEAK: a later conversion to 16-bit does not clip.
|
| 173 |
-
sf.write(args.output, wave.numpy(), model.config.sample_rate, subtype="FLOAT")
|
| 174 |
-
for phones in spoken:
|
| 175 |
-
print(" ".join(phones.symbols))
|
| 176 |
-
loudest = float(raw.abs().max())
|
| 177 |
-
scaled = f", scaled down to {PEAK}" if wave is not raw else ""
|
| 178 |
-
print(f"Saved {len(wave)/model.config.sample_rate:.2f}s in {len(spoken)} utterance{'s' if len(spoken) != 1 else ''}; peak={loudest:.4f}{scaled}")
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
if __name__ == "__main__":
|
| 182 |
-
main()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tiny_voca/model.py
DELETED
|
@@ -1,379 +0,0 @@
|
|
| 1 |
-
"""tiny-voca v2: feed-forward transformer with a pitch-driven source-filter head.
|
| 2 |
-
|
| 3 |
-
All weights start random. Tensor conventions: hidden [B,T,C], frame features
|
| 4 |
-
[B,T], waveform [B,S]. Acoustic frame i is centred on sample ``i * hop``.
|
| 5 |
-
|
| 6 |
-
phoneme + stress + voice -> transformer encoder -> duration predictor
|
| 7 |
-
-> repeat tokens by duration (supervised durations while training)
|
| 8 |
-
-> frame transformer A -> pitch / voicing / energy
|
| 9 |
-
-> frame transformer B -> filter parameters
|
| 10 |
-
-> harmonic pulse train (from pitch) and noise, each shaped by its
|
| 11 |
-
time-varying filter in the STFT domain -> 24 kHz waveform
|
| 12 |
-
|
| 13 |
-
The waveform head has no neural upsampling network. The oscillator supplies the
|
| 14 |
-
periodicity that a tiny decoder cannot render reliably on its own; the network
|
| 15 |
-
only has to predict slowly varying spectral envelopes (complex cepstra), which
|
| 16 |
-
is what keeps the voice from sounding buzzy or unstable at this size.
|
| 17 |
-
"""
|
| 18 |
-
|
| 19 |
-
import math
|
| 20 |
-
import torch
|
| 21 |
-
from torch import nn
|
| 22 |
-
from torch.nn import functional as F
|
| 23 |
-
from .config import Config
|
| 24 |
-
from .text import PHONE_IDS, SYMBOL_TO_ID, VOWELS
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
class UtteranceTooLong(ValueError):
|
| 28 |
-
"""The utterance needs more frames than ``max_frames``: split the input."""
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
def length_mask(lengths, size=None):
|
| 32 |
-
size = int(lengths.max()) if size is None else size
|
| 33 |
-
return torch.arange(size, device=lengths.device)[None, :] < lengths[:, None]
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
def rotary_table(size, width, device):
|
| 37 |
-
inverse = 1.0 / (10000 ** (torch.arange(0, width, 2, device=device, dtype=torch.float32) / width))
|
| 38 |
-
angle = torch.arange(size, device=device, dtype=torch.float32)[:, None] * inverse[None]
|
| 39 |
-
return angle.cos(), angle.sin()
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
def rotate(x, table):
|
| 43 |
-
cos, sin = table[0].to(x.dtype), table[1].to(x.dtype)
|
| 44 |
-
a, b = x[..., 0::2], x[..., 1::2]
|
| 45 |
-
return torch.stack((a * cos - b * sin, a * sin + b * cos), dim=-1).flatten(-2)
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
class Attention(nn.Module):
|
| 49 |
-
"""Self-attention with rotary (relative) positions: no absolute position
|
| 50 |
-
table, so utterances longer than those seen in training stay in range."""
|
| 51 |
-
|
| 52 |
-
def __init__(self, channels, heads, dropout):
|
| 53 |
-
super().__init__()
|
| 54 |
-
self.heads, self.dropout = heads, dropout
|
| 55 |
-
self.qkv = nn.Linear(channels, 3 * channels)
|
| 56 |
-
self.out = nn.Linear(channels, channels)
|
| 57 |
-
|
| 58 |
-
def forward(self, x, mask, table):
|
| 59 |
-
b, t, c = x.shape
|
| 60 |
-
q, k, v = self.qkv(x).view(b, t, 3, self.heads, c // self.heads).permute(2, 0, 3, 1, 4)
|
| 61 |
-
y = F.scaled_dot_product_attention(rotate(q, table), rotate(k, table), v, attn_mask=mask[:, None, None, :],
|
| 62 |
-
dropout_p=self.dropout if self.training else 0.0)
|
| 63 |
-
return self.out(y.transpose(1, 2).reshape(b, t, c))
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
class Block(nn.Module):
|
| 67 |
-
def __init__(self, c):
|
| 68 |
-
super().__init__()
|
| 69 |
-
self.norm1 = nn.LayerNorm(c.channels)
|
| 70 |
-
self.attention = Attention(c.channels, c.heads, c.dropout)
|
| 71 |
-
self.norm2 = nn.LayerNorm(c.channels)
|
| 72 |
-
self.depthwise = nn.Conv1d(c.channels, c.channels, c.kernel, padding=c.kernel // 2, groups=c.channels)
|
| 73 |
-
self.expand = nn.Linear(c.channels, c.feedforward)
|
| 74 |
-
self.project = nn.Linear(c.feedforward, c.channels)
|
| 75 |
-
self.dropout = nn.Dropout(c.dropout)
|
| 76 |
-
|
| 77 |
-
def forward(self, x, mask, table):
|
| 78 |
-
keep = mask[..., None]
|
| 79 |
-
x = (x + self.dropout(self.attention(self.norm1(x), mask, table))) * keep
|
| 80 |
-
# Mask before the convolution so padded positions cannot leak back in.
|
| 81 |
-
y = self.depthwise((self.norm2(x) * keep).transpose(1, 2)).transpose(1, 2)
|
| 82 |
-
y = self.project(self.dropout(F.gelu(self.expand(y))))
|
| 83 |
-
return (x + self.dropout(y)) * keep
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
class Stack(nn.Module):
|
| 87 |
-
def __init__(self, c, layers):
|
| 88 |
-
super().__init__()
|
| 89 |
-
self.blocks = nn.ModuleList(Block(c) for _ in range(layers))
|
| 90 |
-
self.norm = nn.LayerNorm(c.channels)
|
| 91 |
-
self.width = c.channels // c.heads
|
| 92 |
-
|
| 93 |
-
def forward(self, x, mask):
|
| 94 |
-
table = rotary_table(x.shape[1], self.width, x.device)
|
| 95 |
-
for block in self.blocks:
|
| 96 |
-
x = block(x, mask, table)
|
| 97 |
-
return self.norm(x) * mask[..., None]
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
class Predictor(nn.Module):
|
| 101 |
-
def __init__(self, c, outputs):
|
| 102 |
-
super().__init__()
|
| 103 |
-
p = c.predictor_channels
|
| 104 |
-
self.conv1 = nn.Conv1d(c.channels, p, 3, padding=1)
|
| 105 |
-
self.conv2 = nn.Conv1d(p, p, 3, padding=1)
|
| 106 |
-
self.norm1, self.norm2 = nn.LayerNorm(p), nn.LayerNorm(p)
|
| 107 |
-
self.drop = nn.Dropout(c.dropout)
|
| 108 |
-
self.out = nn.Linear(p, outputs)
|
| 109 |
-
|
| 110 |
-
def forward(self, x, mask):
|
| 111 |
-
x = self.conv1((x * mask[..., None]).transpose(1, 2)).transpose(1, 2)
|
| 112 |
-
x = self.drop(self.norm1(F.gelu(x))) * mask[..., None]
|
| 113 |
-
x = self.conv2(x.transpose(1, 2)).transpose(1, 2)
|
| 114 |
-
x = self.drop(self.norm2(F.gelu(x)))
|
| 115 |
-
return self.out(x) * mask[..., None]
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
def pulse_train(f0, sample_rate, hop, limit=0.47, phase=None):
|
| 119 |
-
"""Band-limited pulse train [B, T*hop] with unit power for f0 [B, T] in Hz.
|
| 120 |
-
|
| 121 |
-
Frame values sit at samples i*hop and are interpolated in the log domain.
|
| 122 |
-
The sum of all harmonics below ``limit * sample_rate`` has the closed form
|
| 123 |
-
sin((K+1/2)x) / (2 sin(x/2)) - 1/2; the top harmonic fades in and out so the
|
| 124 |
-
signal stays continuous while the pitch glides. Float64 keeps the phase exact.
|
| 125 |
-
"""
|
| 126 |
-
frames = f0.shape[1]
|
| 127 |
-
knots = torch.log(f0.double().clamp_min(1.0))
|
| 128 |
-
knots = torch.cat((knots, knots[:, -1:]), dim=1)
|
| 129 |
-
position = torch.arange(frames * hop, device=f0.device, dtype=torch.float64) / hop
|
| 130 |
-
low = position.floor().long()
|
| 131 |
-
weight = position - low
|
| 132 |
-
frequency = torch.exp(knots[:, low] * (1 - weight) + knots[:, low + 1] * weight)
|
| 133 |
-
theta = 2 * math.pi * torch.cumsum(frequency / sample_rate, dim=1)
|
| 134 |
-
if phase is not None:
|
| 135 |
-
theta = theta + phase.double()[:, None]
|
| 136 |
-
theta = torch.remainder(theta, 2 * math.pi)
|
| 137 |
-
harmonics = (limit * sample_rate / frequency).clamp_min(1.0)
|
| 138 |
-
whole = torch.floor(harmonics)
|
| 139 |
-
denominator = 2 * torch.sin(theta / 2)
|
| 140 |
-
tiny = denominator.abs() < 1e-7
|
| 141 |
-
core = torch.where(tiny, whole, torch.sin((whole + 0.5) * theta) / torch.where(tiny, torch.ones_like(denominator), denominator) - 0.5)
|
| 142 |
-
wave = core + (harmonics - whole) * torch.cos((whole + 1) * theta)
|
| 143 |
-
return (wave * torch.sqrt(2.0 / harmonics)).float()
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
def filtered(source, response, fft, hop, window):
|
| 147 |
-
"""Time-varying filtering: response [B, frames, bins] multiplies the STFT."""
|
| 148 |
-
spectrum = torch.stft(source, fft, hop, window=window, center=True, pad_mode="constant", return_complex=True)
|
| 149 |
-
if spectrum.shape[-1] != response.shape[1]:
|
| 150 |
-
raise ValueError("filter frames do not match the source")
|
| 151 |
-
return torch.istft(spectrum * response.transpose(1, 2), fft, hop, window=window, center=True, length=source.shape[-1])
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
def cepstrum_response(causal, anticausal, fft):
|
| 155 |
-
"""Complex frequency response exp(FFT(cepstrum)). Causal coefficients give a
|
| 156 |
-
minimum-phase filter; anticausal ones add a maximum-phase part (glottal pulse)."""
|
| 157 |
-
buffer = causal.new_zeros(*causal.shape[:-1], fft)
|
| 158 |
-
buffer[..., :causal.shape[-1]] = causal
|
| 159 |
-
if anticausal is not None:
|
| 160 |
-
buffer[..., fft - anticausal.shape[-1]:] = anticausal.flip(-1)
|
| 161 |
-
spectrum = torch.fft.rfft(buffer, dim=-1)
|
| 162 |
-
return torch.polar(torch.exp(spectrum.real.clamp(-14, 6)), spectrum.imag)
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
class SourceFilter(nn.Module):
|
| 166 |
-
"""Harmonic-plus-noise synthesis controlled per frame by two linear heads."""
|
| 167 |
-
|
| 168 |
-
def __init__(self, c):
|
| 169 |
-
super().__init__()
|
| 170 |
-
self.config = c
|
| 171 |
-
self.harmonic_steps, self.noise_steps = c.hop // c.synth_hop, c.hop // c.noise_hop
|
| 172 |
-
self.harmonic = nn.Linear(c.channels, c.cep_causal + c.cep_anti + self.harmonic_steps)
|
| 173 |
-
self.noise = nn.Linear(c.channels, c.noise_cep + self.noise_steps)
|
| 174 |
-
for head, level in ((self.harmonic, -1.5), (self.noise, -2.5)): # start quiet and spectrally flat
|
| 175 |
-
nn.init.zeros_(head.weight)
|
| 176 |
-
nn.init.zeros_(head.bias)
|
| 177 |
-
head.bias.data[0] = level
|
| 178 |
-
|
| 179 |
-
def lifter(size, first):
|
| 180 |
-
scale = 1.0 / (1.0 + torch.arange(first, first + size, dtype=torch.float32) / 4)
|
| 181 |
-
if first == 0:
|
| 182 |
-
scale[0] = 2.0 # coefficient 0 is the log gain and needs range
|
| 183 |
-
return scale
|
| 184 |
-
self.register_buffer("causal_lifter", lifter(c.cep_causal, 0), persistent=False)
|
| 185 |
-
self.register_buffer("anti_lifter", lifter(c.cep_anti, 1), persistent=False)
|
| 186 |
-
self.register_buffer("noise_lifter", lifter(c.noise_cep, 0), persistent=False)
|
| 187 |
-
self.register_buffer("synth_window", torch.hann_window(c.synth_fft), persistent=False)
|
| 188 |
-
self.register_buffer("noise_window", torch.hann_window(c.noise_fft), persistent=False)
|
| 189 |
-
|
| 190 |
-
@staticmethod
|
| 191 |
-
def _take(values, index):
|
| 192 |
-
return values.gather(1, index[..., None].expand(-1, -1, values.shape[-1]))
|
| 193 |
-
|
| 194 |
-
def _subframes(self, frames, lengths, steps):
|
| 195 |
-
"""Sub-frame j uses frame j // steps; indices past an utterance's end
|
| 196 |
-
repeat its last sub-frame so padding never changes real audio. Two extra
|
| 197 |
-
sub-frames cover the half window of zeros appended to the source."""
|
| 198 |
-
sub = torch.arange(steps * frames + 3, device=lengths.device)[None].expand(len(lengths), -1)
|
| 199 |
-
return torch.minimum(sub, (steps * lengths - 1).clamp_min(0)[:, None])
|
| 200 |
-
|
| 201 |
-
@staticmethod
|
| 202 |
-
def _shape(source, response, fft, hop, window):
|
| 203 |
-
# Half a window of trailing zeros: the frames around an utterance's end are
|
| 204 |
-
# then the same whether it stands alone or is padded inside a batch.
|
| 205 |
-
return filtered(F.pad(source, (0, fft // 2)), response, fft, hop, window)[:, :source.shape[-1]]
|
| 206 |
-
|
| 207 |
-
def forward(self, hidden, f0, lengths, noise=None, phase=None):
|
| 208 |
-
c = self.config
|
| 209 |
-
frames = hidden.shape[1]
|
| 210 |
-
samples = frames * c.hop
|
| 211 |
-
with torch.autocast(device_type=hidden.device.type, enabled=False):
|
| 212 |
-
hidden = hidden.float()
|
| 213 |
-
audible = length_mask(lengths * c.hop, samples)
|
| 214 |
-
last = (lengths - 1).clamp_min(0)[:, None]
|
| 215 |
-
# Harmonic branch: envelope interpolated between frames, one gain per sub-frame.
|
| 216 |
-
h = self.harmonic(hidden)
|
| 217 |
-
split = c.cep_causal + c.cep_anti
|
| 218 |
-
sub = self._subframes(frames, lengths, self.harmonic_steps)
|
| 219 |
-
here, following = sub // self.harmonic_steps, torch.minimum((sub + 1) // self.harmonic_steps, last)
|
| 220 |
-
causal = 0.5 * (self._take(h[..., :c.cep_causal], here) + self._take(h[..., :c.cep_causal], following)) * self.causal_lifter
|
| 221 |
-
anti = 0.5 * (self._take(h[..., c.cep_causal:split], here) + self._take(h[..., c.cep_causal:split], following)) * self.anti_lifter
|
| 222 |
-
causal = torch.cat((causal[..., :1] + h[..., split:].flatten(1).gather(1, sub)[..., None], causal[..., 1:]), dim=-1)
|
| 223 |
-
harmonic_response = cepstrum_response(causal, anti, c.synth_fft)
|
| 224 |
-
# Noise branch: one envelope per frame, four gains per frame for sharp consonants.
|
| 225 |
-
n = self.noise(hidden)
|
| 226 |
-
sub = self._subframes(frames, lengths, self.noise_steps)
|
| 227 |
-
shape = self._take(n[..., :c.noise_cep], sub // self.noise_steps) * self.noise_lifter
|
| 228 |
-
shape = torch.cat((shape[..., :1] + n[..., c.noise_cep:].flatten(1).gather(1, sub)[..., None], shape[..., 1:]), dim=-1)
|
| 229 |
-
noise_response = cepstrum_response(shape, None, c.noise_fft)
|
| 230 |
-
# Hold the last real pitch value through padding: the pitch glide inside an
|
| 231 |
-
# utterance's final frame must not depend on what the batch was padded with.
|
| 232 |
-
f0 = f0.float().gather(1, torch.minimum(torch.arange(frames, device=f0.device)[None], last))
|
| 233 |
-
pulses = pulse_train(f0, c.sample_rate, c.hop, c.harmonic_limit, phase) * audible
|
| 234 |
-
if noise is None:
|
| 235 |
-
noise = torch.randn(hidden.shape[0], samples, device=hidden.device)
|
| 236 |
-
wave = (self._shape(pulses, harmonic_response, c.synth_fft, c.synth_hop, self.synth_window)
|
| 237 |
-
+ self._shape(noise * audible, noise_response, c.noise_fft, c.noise_hop, self.noise_window))
|
| 238 |
-
return wave * audible
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
class TinyVoca(nn.Module):
|
| 242 |
-
def __init__(self, config=Config()):
|
| 243 |
-
super().__init__()
|
| 244 |
-
self.config = c = config
|
| 245 |
-
self.tokens = nn.Embedding(c.vocab_size, c.channels, padding_idx=0)
|
| 246 |
-
self.stress = nn.Embedding(3, c.channels)
|
| 247 |
-
self.voices = nn.Embedding(len(c.speakers), c.channels)
|
| 248 |
-
self.encoder = Stack(c, c.encoder_layers)
|
| 249 |
-
# Outputs per token: log(1 + frames) and, for pause-capable tokens, a
|
| 250 |
-
# "has frames at all" logit. A pause is absent more often than present, so
|
| 251 |
-
# one regression would average both cases into a pause that is too short.
|
| 252 |
-
self.duration = Predictor(c, 2)
|
| 253 |
-
self.frame_voices = nn.Embedding(len(c.speakers), c.channels)
|
| 254 |
-
self.frame_position = nn.Linear(3, c.channels)
|
| 255 |
-
self.prosody_stack = Stack(c, c.prosody_layers)
|
| 256 |
-
# Outputs: continuous log(F0/reference), voiced logit, normalized log RMS energy.
|
| 257 |
-
self.prosody_head = nn.Linear(c.channels, 3)
|
| 258 |
-
self.prosody_projection = nn.Linear(3, c.channels)
|
| 259 |
-
self.acoustic_stack = Stack(c, c.acoustic_layers)
|
| 260 |
-
self.vocoder = SourceFilter(c)
|
| 261 |
-
phones = torch.zeros(c.vocab_size, dtype=torch.bool)
|
| 262 |
-
phones[sorted(PHONE_IDS)] = True
|
| 263 |
-
self.register_buffer("phone_tokens", phones, persistent=False)
|
| 264 |
-
vowels = torch.zeros(c.vocab_size, dtype=torch.bool)
|
| 265 |
-
vowels[[SYMBOL_TO_ID[v] for v in VOWELS]] = True
|
| 266 |
-
self.register_buffer("vowel_tokens", vowels, persistent=False)
|
| 267 |
-
|
| 268 |
-
def encode(self, tokens, stress, lengths, speakers):
|
| 269 |
-
if tokens.ndim != 2 or stress.shape != tokens.shape or lengths.shape != (tokens.shape[0],) or speakers.shape != lengths.shape:
|
| 270 |
-
raise ValueError("expected tokens[B,N], stress[B,N], lengths[B], speakers[B]")
|
| 271 |
-
if tokens.shape[1] > self.config.max_tokens or bool((lengths < 1).any()) or bool((lengths > tokens.shape[1]).any()):
|
| 272 |
-
raise ValueError("invalid token length")
|
| 273 |
-
mask = length_mask(lengths, tokens.shape[1])
|
| 274 |
-
x = (self.tokens(tokens) + self.stress(stress) + self.voices(speakers)[:, None]) * mask[..., None]
|
| 275 |
-
return self.encoder(x, mask), mask
|
| 276 |
-
|
| 277 |
-
def expand(self, hidden, durations, token_mask, speakers):
|
| 278 |
-
"""Repeat token states by integer durations (zero is allowed for pause
|
| 279 |
-
tokens) and add each frame's position inside its token."""
|
| 280 |
-
if durations.shape != token_mask.shape or bool((durations < 0).any()) or bool((durations[~token_mask] != 0).any()):
|
| 281 |
-
raise ValueError("invalid durations")
|
| 282 |
-
lengths = durations.sum(1)
|
| 283 |
-
if bool((lengths < 1).any()):
|
| 284 |
-
raise ValueError("utterance has no frames")
|
| 285 |
-
if bool((lengths > self.config.max_frames).any()):
|
| 286 |
-
raise UtteranceTooLong("utterance exceeds max_frames; split the input")
|
| 287 |
-
size = int(lengths.max())
|
| 288 |
-
ends = durations.cumsum(1)
|
| 289 |
-
frame = torch.arange(size, device=hidden.device)[None].expand(hidden.shape[0], size).contiguous()
|
| 290 |
-
index = torch.searchsorted(ends, frame, right=True).clamp(max=durations.shape[1] - 1)
|
| 291 |
-
owned = durations.gather(1, index).clamp_min(1)
|
| 292 |
-
offset = frame - (ends.gather(1, index) - durations.gather(1, index))
|
| 293 |
-
relative = (offset.to(hidden.dtype) + 0.5) / owned
|
| 294 |
-
features = torch.stack((relative, 1 - relative, torch.log1p(owned.to(hidden.dtype)) / 4), dim=-1)
|
| 295 |
-
mask = frame < lengths[:, None]
|
| 296 |
-
expanded = hidden.gather(1, index[..., None].expand(-1, -1, hidden.shape[-1]))
|
| 297 |
-
expanded = expanded + self.frame_position(features) + self.frame_voices(speakers)[:, None]
|
| 298 |
-
return expanded * mask[..., None], mask, lengths
|
| 299 |
-
|
| 300 |
-
def predict_prosody(self, frames, frame_mask):
|
| 301 |
-
hidden = self.prosody_stack(frames, frame_mask)
|
| 302 |
-
return hidden, self.prosody_head(hidden) * frame_mask[..., None]
|
| 303 |
-
|
| 304 |
-
@staticmethod
|
| 305 |
-
def hard_prosody(prediction):
|
| 306 |
-
"""What the decoder is conditioned on when it is not teacher-forced."""
|
| 307 |
-
return torch.stack((prediction[..., 0].clamp(-2.0, 1.5), (prediction[..., 1] > 0).to(prediction.dtype),
|
| 308 |
-
prediction[..., 2].clamp(-4.5, 3.0)), dim=-1)
|
| 309 |
-
|
| 310 |
-
def decode(self, prosody_hidden, condition, frame_mask):
|
| 311 |
-
return self.acoustic_stack((prosody_hidden + self.prosody_projection(condition)) * frame_mask[..., None], frame_mask)
|
| 312 |
-
|
| 313 |
-
def frequency(self, log_f0):
|
| 314 |
-
c = self.config
|
| 315 |
-
return (c.pitch_reference_hz * torch.exp(log_f0.float())).clamp(c.f0_min, c.f0_max)
|
| 316 |
-
|
| 317 |
-
def predict_durations(self, hidden, mask, tokens, speed=1.0):
|
| 318 |
-
output = self.duration(hidden, mask).float()
|
| 319 |
-
frames = torch.round(torch.expm1(output[..., 0].clamp(0, math.log1p(400))) / speed).long().clamp_min(1)
|
| 320 |
-
# Every phoneme is audible for at least one frame. A pause-capable token
|
| 321 |
-
# (edge, punctuation, word boundary) lasts its predicted length when the
|
| 322 |
-
# presence logit says there is a pause, and vanishes otherwise.
|
| 323 |
-
present = self.phone_tokens[tokens] | (output[..., 1] > 0)
|
| 324 |
-
return torch.where(present, frames, torch.zeros_like(frames)) * mask
|
| 325 |
-
|
| 326 |
-
@staticmethod
|
| 327 |
-
def widen_pitch(prosody, frame_mask, pitch_range):
|
| 328 |
-
"""Scale the predicted pitch movement around each utterance's voiced mean.
|
| 329 |
-
Regression predicts a flatter contour than the recordings; values above 1
|
| 330 |
-
restore range (1.0 leaves the prediction untouched)."""
|
| 331 |
-
if pitch_range == 1.0:
|
| 332 |
-
return prosody
|
| 333 |
-
voiced = ((prosody[..., 1] > 0) & frame_mask).to(prosody.dtype)
|
| 334 |
-
mean = (prosody[..., 0] * voiced).sum(1, keepdim=True) / voiced.sum(1, keepdim=True).clamp_min(1)
|
| 335 |
-
pitch = mean + (prosody[..., 0] - mean) * pitch_range
|
| 336 |
-
return torch.cat((pitch[..., None], prosody[..., 1:]), dim=-1) * frame_mask[..., None]
|
| 337 |
-
|
| 338 |
-
@staticmethod
|
| 339 |
-
def pitch_wobble(shape, semitones, seed, device):
|
| 340 |
-
"""Small random pitch movement for the oscillator only (log-F0 units).
|
| 341 |
-
Recorded pitch has cycle-to-cycle irregularity that a predicted contour
|
| 342 |
-
lacks; two thirds of the wobble is slow drift, one third frame-level."""
|
| 343 |
-
generator = torch.Generator().manual_seed(seed + 7919)
|
| 344 |
-
fast = torch.randn(shape, generator=generator)
|
| 345 |
-
slow = F.avg_pool1d(torch.randn(shape[0], 1, shape[1] + 16, generator=generator), 17, stride=1)[:, 0]
|
| 346 |
-
slow = slow / slow.std().clamp_min(1e-6)
|
| 347 |
-
return ((2 * slow + fast) / 5 ** 0.5 * semitones * math.log(2) / 12).to(device)
|
| 348 |
-
|
| 349 |
-
@torch.inference_mode()
|
| 350 |
-
def synthesize(self, tokens, stress, lengths, speakers, speed=1.0, pitch_shift=0.0, seed=0, pitch_range=1.0, pitch_jitter=0.0,
|
| 351 |
-
voiced_vowels=True):
|
| 352 |
-
"""Free-running synthesis: predicted durations, pitch, voicing and energy."""
|
| 353 |
-
if not math.isfinite(speed) or not 0.25 <= speed <= 4 or not math.isfinite(pitch_shift) or not 0 <= pitch_range <= 3:
|
| 354 |
-
raise ValueError("speed must be between 0.25 and 4, pitch_shift finite and pitch_range between 0 and 3")
|
| 355 |
-
hidden, mask = self.encode(tokens, stress, lengths, speakers)
|
| 356 |
-
durations = self.predict_durations(hidden, mask, tokens, speed)
|
| 357 |
-
frames, frame_mask, frame_lengths = self.expand(hidden, durations, mask, speakers)
|
| 358 |
-
prosody_hidden, prosody = self.predict_prosody(frames, frame_mask)
|
| 359 |
-
if voiced_vowels:
|
| 360 |
-
# The pitch tracker missed creaky vowels in the recordings, and the
|
| 361 |
-
# voicing predictor learned to drop whole vowels (heard as a whispered
|
| 362 |
-
# word). A vowel is voiced by definition, so its frames are kept voiced.
|
| 363 |
-
ends = durations.cumsum(1)
|
| 364 |
-
frame = torch.arange(frames.shape[1], device=tokens.device)[None].expand(len(lengths), -1).contiguous()
|
| 365 |
-
owner = torch.searchsorted(ends, frame, right=True).clamp(max=tokens.shape[1] - 1)
|
| 366 |
-
vowel = self.vowel_tokens[tokens].gather(1, owner) & frame_mask
|
| 367 |
-
prosody = torch.cat((prosody[..., :1], torch.where(vowel, prosody[..., 1].clamp_min(2.0), prosody[..., 1])[..., None],
|
| 368 |
-
prosody[..., 2:]), dim=-1)
|
| 369 |
-
prosody = self.widen_pitch(prosody, frame_mask, pitch_range)
|
| 370 |
-
acoustic = self.decode(prosody_hidden, self.hard_prosody(prosody), frame_mask)
|
| 371 |
-
# One noise stream per row, drawn at the row's own length, so batching or
|
| 372 |
-
# padding never changes a row's audio.
|
| 373 |
-
noise = nn.utils.rnn.pad_sequence([torch.randn(int(n) * self.config.hop, generator=torch.Generator().manual_seed(seed + row))
|
| 374 |
-
for row, n in enumerate(frame_lengths)], batch_first=True)
|
| 375 |
-
pitch = prosody[..., 0] + pitch_shift
|
| 376 |
-
if pitch_jitter > 0:
|
| 377 |
-
pitch = pitch + self.pitch_wobble(pitch.shape, pitch_jitter, seed, pitch.device)
|
| 378 |
-
wave = self.vocoder(acoustic, self.frequency(pitch), frame_lengths, noise=noise.to(hidden.device))
|
| 379 |
-
return wave, frame_lengths * self.config.hop, {"durations": durations, "prosody": prosody, "frame_mask": frame_mask}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tiny_voca/text.py
DELETED
|
@@ -1,219 +0,0 @@
|
|
| 1 |
-
"""Japanese front end: text -> phoneme tokens with a pitch-accent feature.
|
| 2 |
-
|
| 3 |
-
The same code runs during annotation, training-set preparation and inference,
|
| 4 |
-
so tokens can never drift between them.
|
| 5 |
-
|
| 6 |
-
* pyopenjtalk (OpenJTalk with its NAIST-JDIC dictionary) reads the text: kanji
|
| 7 |
-
readings, numbers, and the accent phrases with their accent types.
|
| 8 |
-
* A token is one OpenJTalk phoneme (``k``, ``sh``, ``a``, ``N``, ``cl``, ...).
|
| 9 |
-
A long vowel is two tokens (``o o``), one per mora. Vowels that OpenJTalk
|
| 10 |
-
devoices (``desU``, ``shIta``) are their own tokens, ``A I U E O``: they are
|
| 11 |
-
not voiced, and the voicing rules for vowels must not touch them.
|
| 12 |
-
* The per-token feature that the model calls ``stress`` carries the Tokyo
|
| 13 |
-
pitch-accent tone of the token's mora: 1 low, 2 high, 0 for everything that
|
| 14 |
-
is not a phone. It is derived from the accent type and the mora position in
|
| 15 |
-
the accent phrase (full-context fields F1/F2 and A2).
|
| 16 |
-
* Accent-phrase boundaries are ``<sp>`` tokens, punctuation marks are tokens,
|
| 17 |
-
and so are the utterance edges. They may last zero frames and carry the
|
| 18 |
-
pauses when the recording has them.
|
| 19 |
-
"""
|
| 20 |
-
|
| 21 |
-
from dataclasses import dataclass
|
| 22 |
-
import hashlib
|
| 23 |
-
import json
|
| 24 |
-
import re
|
| 25 |
-
import unicodedata
|
| 26 |
-
|
| 27 |
-
FRONTEND_VERSION = 1
|
| 28 |
-
|
| 29 |
-
PAD, BOS, EOS, SP, UNK = "<pad>", "<bos>", "<eos>", "<sp>", "<unk>"
|
| 30 |
-
SPECIALS = (PAD, BOS, EOS, SP, UNK)
|
| 31 |
-
PUNCTUATION = (",", ".", "?", "!", ";", ":", '"', "(", ")", "—", "…")
|
| 32 |
-
CONSONANTS = ("k", "ky", "kw", "g", "gy", "gw", "s", "sh", "z", "j", "t", "ty", "ch", "ts", "d", "dy", "n", "ny",
|
| 33 |
-
"h", "hy", "f", "b", "by", "p", "py", "m", "my", "y", "r", "ry", "w", "v", "N", "cl")
|
| 34 |
-
VOWELS = ("a", "i", "u", "e", "o")
|
| 35 |
-
DEVOICED = ("A", "I", "U", "E", "O")
|
| 36 |
-
PHONES = CONSONANTS + VOWELS + DEVOICED
|
| 37 |
-
# Append-only: changing the order or removing a symbol invalidates checkpoints.
|
| 38 |
-
SYMBOLS = SPECIALS + PUNCTUATION + PHONES
|
| 39 |
-
SYMBOL_TO_ID = {symbol: index for index, symbol in enumerate(SYMBOLS)}
|
| 40 |
-
PHONE_SET = frozenset(PHONES)
|
| 41 |
-
PHONE_IDS = frozenset(SYMBOL_TO_ID[p] for p in PHONES) | {SYMBOL_TO_ID[UNK]}
|
| 42 |
-
VOICELESS = frozenset(("k", "ky", "kw", "s", "sh", "t", "ty", "ch", "ts", "h", "hy", "f", "p", "py", "cl") + DEVOICED)
|
| 43 |
-
VOWEL_SET = frozenset(VOWELS)
|
| 44 |
-
LOW, HIGH = 1, 2
|
| 45 |
-
|
| 46 |
-
# Full-width and typographic marks to the inventory. NFKC already turns
|
| 47 |
-
# full-width ASCII (?!,.:;()) into ASCII.
|
| 48 |
-
_MARKS = str.maketrans({"、": ",", ",": ",", "。": ".", "。": ".", "、": ",", "‥": "…", "―": "—", "–": "—",
|
| 49 |
-
"「": '"', "」": '"', "『": '"', "』": '"', "“": '"', "”": '"', "„": '"', "«": '"', "»": '"',
|
| 50 |
-
"【": "(", "】": ")", "〔": "(", "〕": ")", "[": "(", "]": ")", "[": "(", "]": ")"})
|
| 51 |
-
_PUNCTUATION_CHARS = frozenset(PUNCTUATION)
|
| 52 |
-
# Separate words but say nothing: a boundary between accent phrases.
|
| 53 |
-
_SEPARATORS = frozenset("・ ")
|
| 54 |
-
# The phone, its mora position in the accent phrase (A2), the phrase's mora
|
| 55 |
-
# count and accent type (F1, F2) and its position in the breath group (F5).
|
| 56 |
-
_LABEL = re.compile(r"-(?P<phone>[^+]+)\+.*?/A:(?:-?\d+|xx)\+(?P<a2>\d+|xx)\+.*?/F:(?P<f1>\d+|xx)_(?P<f2>\d+|xx)"
|
| 57 |
-
r"#(?:\d+|xx)_(?:\d+|xx)@(?P<f5>\d+|xx)_")
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
class NothingToPronounce(ValueError):
|
| 61 |
-
"""The text has nothing to say: only marks, emoji and the like."""
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
@dataclass(frozen=True)
|
| 65 |
-
class Phonemized:
|
| 66 |
-
symbols: tuple
|
| 67 |
-
ids: tuple
|
| 68 |
-
stress: tuple # pitch-accent tone per token: 0 none, 1 low, 2 high
|
| 69 |
-
unknown: tuple # OpenJTalk phonemes that are not in the inventory
|
| 70 |
-
|
| 71 |
-
def __len__(self):
|
| 72 |
-
return len(self.ids)
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
def _pyopenjtalk():
|
| 76 |
-
try:
|
| 77 |
-
import pyopenjtalk
|
| 78 |
-
except ImportError as error:
|
| 79 |
-
raise RuntimeError("the Japanese front end needs pyopenjtalk: pip install pyopenjtalk") from error
|
| 80 |
-
return pyopenjtalk
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
def frontend_identity():
|
| 84 |
-
return {"frontend_version": FRONTEND_VERSION, "phonemizer": "pyopenjtalk", "symbols": list(SYMBOLS),
|
| 85 |
-
"tone": "Tokyo H/L from accent type and mora position"}
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
def frontend_runtime():
|
| 89 |
-
"""What an annotation run records about the program behind its tokens."""
|
| 90 |
-
return {"pyopenjtalk": _pyopenjtalk().__version__}
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
def frontend_fingerprint():
|
| 94 |
-
return hashlib.sha256(json.dumps(frontend_identity(), sort_keys=True, ensure_ascii=False).encode()).hexdigest()
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
def normalize_text(text):
|
| 98 |
-
text = unicodedata.normalize("NFKC", text).translate(_MARKS)
|
| 99 |
-
text = re.sub(r"\.{3,}", "…", text)
|
| 100 |
-
text = re.sub(r"-{2,}|\s-\s", "—", text)
|
| 101 |
-
return re.sub(r"\s+", " ", text).strip()
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
def chunks(text):
|
| 105 |
-
"""Yield ``(is_punctuation, piece)`` for normalized text. Decimal points and
|
| 106 |
-
digit-group commas stay inside the text piece for OpenJTalk; a separator
|
| 107 |
-
(space, ・) ends a piece without a token of its own."""
|
| 108 |
-
start = 0
|
| 109 |
-
for i, char in enumerate(text):
|
| 110 |
-
if char in _SEPARATORS:
|
| 111 |
-
if text[start:i].strip():
|
| 112 |
-
yield False, text[start:i].strip()
|
| 113 |
-
start = i + 1
|
| 114 |
-
continue
|
| 115 |
-
if char not in _PUNCTUATION_CHARS:
|
| 116 |
-
continue
|
| 117 |
-
previous = text[i - 1] if i else ""
|
| 118 |
-
following = text[i + 1] if i + 1 < len(text) else ""
|
| 119 |
-
if char in ".,:" and previous.isdigit() and following.isdigit():
|
| 120 |
-
continue
|
| 121 |
-
if text[start:i].strip():
|
| 122 |
-
yield False, text[start:i].strip()
|
| 123 |
-
yield True, char
|
| 124 |
-
start = i + 1
|
| 125 |
-
if text[start:].strip():
|
| 126 |
-
yield False, text[start:].strip()
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
def tone(mora_position, accent_type):
|
| 130 |
-
"""Tokyo pitch accent of a mora: high or low.
|
| 131 |
-
|
| 132 |
-
Type 0 (heiban) rises after the first mora and stays high; type 1 starts
|
| 133 |
-
high and falls; type n > 1 rises after the first mora and falls after the
|
| 134 |
-
n-th."""
|
| 135 |
-
if accent_type == 1:
|
| 136 |
-
return HIGH if mora_position == 1 else LOW
|
| 137 |
-
if mora_position == 1:
|
| 138 |
-
return LOW
|
| 139 |
-
return HIGH if accent_type == 0 or mora_position <= accent_type else LOW
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
def accent_phrases(labels):
|
| 143 |
-
"""OpenJTalk full-context labels -> accent phrases as lists of ``(phone, tone)``.
|
| 144 |
-
A pause inside a piece also ends the phrase."""
|
| 145 |
-
phrases, current, phrase = [], [], None
|
| 146 |
-
for label in labels:
|
| 147 |
-
match = _LABEL.search(label)
|
| 148 |
-
if match is None:
|
| 149 |
-
raise ValueError(f"unexpected OpenJTalk label: {label}")
|
| 150 |
-
if match["phone"] in ("sil", "pau") or match["a2"] == "xx":
|
| 151 |
-
if current:
|
| 152 |
-
phrases.append(current)
|
| 153 |
-
current, phrase = [], None
|
| 154 |
-
continue
|
| 155 |
-
if current and match["f5"] != phrase:
|
| 156 |
-
phrases.append(current)
|
| 157 |
-
current = []
|
| 158 |
-
current.append((match["phone"], tone(int(match["a2"]), int(match["f2"]))))
|
| 159 |
-
phrase = match["f5"]
|
| 160 |
-
if current:
|
| 161 |
-
phrases.append(current)
|
| 162 |
-
return phrases
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
def tokenize(pieces):
|
| 166 |
-
"""Build the token sequence from ``(is_punctuation, value)`` pieces where a
|
| 167 |
-
text piece's value is a list of accent phrases, each a list of
|
| 168 |
-
``(phone, tone)``. Pure function (testable without OpenJTalk)."""
|
| 169 |
-
symbols, stress, unknown = [BOS], [0], []
|
| 170 |
-
for punctuation, value in pieces:
|
| 171 |
-
if punctuation:
|
| 172 |
-
if symbols[-1] != value: # collapse repeats such as "!!"
|
| 173 |
-
symbols.append(value)
|
| 174 |
-
stress.append(0)
|
| 175 |
-
continue
|
| 176 |
-
for phrase in value:
|
| 177 |
-
if symbols[-1] in PHONE_SET or symbols[-1] == UNK:
|
| 178 |
-
symbols.append(SP)
|
| 179 |
-
stress.append(0)
|
| 180 |
-
for phone, level in phrase:
|
| 181 |
-
if phone not in PHONE_SET:
|
| 182 |
-
unknown.append(phone)
|
| 183 |
-
phone = UNK
|
| 184 |
-
symbols.append(phone)
|
| 185 |
-
stress.append(level)
|
| 186 |
-
symbols.append(EOS)
|
| 187 |
-
stress.append(0)
|
| 188 |
-
if not any(s in PHONE_SET or s == UNK for s in symbols):
|
| 189 |
-
raise NothingToPronounce("the text has nothing to pronounce")
|
| 190 |
-
return Phonemized(tuple(symbols), tuple(SYMBOL_TO_ID[s] for s in symbols), tuple(stress), tuple(unknown))
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
def phonemize(text):
|
| 194 |
-
if not isinstance(text, str) or not text.strip():
|
| 195 |
-
raise ValueError("text must not be empty")
|
| 196 |
-
openjtalk = _pyopenjtalk()
|
| 197 |
-
pieces = []
|
| 198 |
-
for punctuation, piece in chunks(normalize_text(text)):
|
| 199 |
-
pieces.append((True, piece) if punctuation else (False, accent_phrases(openjtalk.extract_fullcontext(piece))))
|
| 200 |
-
return tokenize(pieces)
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
def is_phone(token_ids):
|
| 204 |
-
"""Boolean list/tensor helper: tokens that must be realised as audio."""
|
| 205 |
-
return [int(i) in PHONE_IDS for i in token_ids]
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
def morae(symbols):
|
| 209 |
-
"""The morae of a token sequence as strings of their phones (``"ky o"``,
|
| 210 |
-
``"N"``, ``"cl"``). A mora ends with a vowel, a devoiced vowel, ``N`` or
|
| 211 |
-
``cl``; any other token in between is skipped."""
|
| 212 |
-
result, onset = [], []
|
| 213 |
-
for symbol in symbols:
|
| 214 |
-
if symbol in VOWEL_SET or symbol in DEVOICED or symbol in ("N", "cl"):
|
| 215 |
-
result.append(" ".join(onset + [symbol]))
|
| 216 |
-
onset = []
|
| 217 |
-
elif symbol in PHONE_SET:
|
| 218 |
-
onset.append(symbol)
|
| 219 |
-
return result
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|