Add ChatTTS example

wasmedge-chatTTS/.gitignore

@@ -0,0 +1,2 @@
+asset
+config

wasmedge-chatTTS/Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "wasmedge-chattts"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]
+serde_json = "1.0"
+wasmedge-wasi-nn = {path = "../../wasmedge-wasi-nn/rust", version = "0.8.0"}
+hound = "3.4"

wasmedge-chatTTS/README.md

@@ -0,0 +1,69 @@
+# ChatTTS example with WasmEdge WASI-NN ChatTTS plugin
+This example demonstrates how to use the WasmEdge WASI-NN ChatTTS plugin to generate speech from text. ChatTTS is a text-to-speech model designed specifically for dialogue scenarios such as LLM assistant. This example will use the WasmEdge WASI-NN ChatTTS plugin to run the ChatTTS to generate speech.
+
+## Install WasmEdge with WASI-NN ChatTTS plugin
+The ChatTTS backend relies on ChatTTS and Python library, we recommend the following commands to install the dependencies.
+``` bash
+sudo apt update
+sudo apt upgrade
+sudo apt install python3-dev
+pip install chattts==0.1.1
+```
+
+Then build and install WasmEdge from source.
+
+``` bash
+cd <path/to/your/wasmedge/source/folder>
+
+cmake -GNinja -Bbuild -DCMAKE_BUILD_TYPE=Release -DWASMEDGE_PLUGIN_WASI_NN_BACKEND="chatTTS"
+cmake --build build
+
+# For the WASI-NN plugin, you should install this project.
+cmake --install build
+```
+
+Then you will have an executable `wasmedge` runtime under `/usr/local/bin` and the WASI-NN with Neural Speed backend plug-in under `/usr/local/lib/wasmedge/libwasmedgePluginWasiNN.so` after installation.
+
+## Build wasm
+
+Run the following command to build wasm, the output WASM file will be at `target/wasm32-wasi/release/`
+
+```bash
+cargo build --target wasm32-wasi --release
+```
+
+## Execute
+
+Execute the WASM with the `wasmedge`.
+
+``` bash
+wasmedge --dir .:.  ./target/wasm32-wasi/release/wasmedge-chattts.wasm
+```
+
+Then you will generate the `output1.wav` file. It is the wav file of the input text.
+
+## Advanced Options
+
+The `config_data` is used to adjust the configuration of the ChatTTS.
+Supports the following options:
+- `prompt`: Generate the special token in the text to synthesize.
+- `spk_emb`: Sampled speaker (Using `random` for random speaker).
+- `temperature`: Custom temperature.
+- `top_k`: Top P decode.
+- `top_p`: Top K decode.
+
+``` rust
+let config_data = serde_json::to_string(&json!({"prompt": "[oral_2][laugh_0][break_6]", "spk_emb": "random", "temperature": 0.5, "top_k": 0, "top_p": 0.9}))
+        .unwrap()
+        .as_bytes()
+        .to_vec();
+```
+<table>
+<tr>
+<td>
+
+[demo.webm](https://github.com/user-attachments/assets/377e0487-9107-41db-9c22-31962ce53f88)
+
+</td>
+</tr>
+</table>

wasmedge-chatTTS/src/main.rs

@@ -0,0 +1,55 @@
+use hound;
+use serde_json::json;
+use wasmedge_wasi_nn::{
+    self, ExecutionTarget, GraphBuilder, GraphEncoding, GraphExecutionContext, TensorType,
+};
+
+fn get_data_from_context(context: &GraphExecutionContext, index: usize) -> Vec<u8> {
+    const MAX_OUTPUT_BUFFER_SIZE: usize = 4096 * 4096;
+    let mut output_buffer = vec![0u8; MAX_OUTPUT_BUFFER_SIZE];
+    let bytes_written = context
+        .get_output(index, &mut output_buffer)
+        .expect("Failed to get output");
+
+    return output_buffer[..bytes_written].to_vec();
+}
+
+fn main() {
+    let prompt = "It is test sentence [uv_break] for chat T T S.";
+    let tensor_data = prompt.as_bytes().to_vec();
+    let config_data = serde_json::to_string(&json!({"prompt": "[oral_2][laugh_0][break_6]", "spk_emb": "random", "temperature": 0.5, "top_k": 0, "top_p": 0.9}))
+        .unwrap()
+        .as_bytes()
+        .to_vec();
+    let empty_vec: Vec<Vec<u8>> = Vec::new();
+    let graph = GraphBuilder::new(GraphEncoding::ChatTTS, ExecutionTarget::CPU)
+        .build_from_bytes(empty_vec)
+        .expect("Failed to build graph");
+    let mut context = graph
+        .init_execution_context()
+        .expect("Failed to init context");
+    context
+        .set_input(0, TensorType::U8, &[1], &tensor_data)
+        .expect("Failed to set input");
+    context
+        .set_input(1, TensorType::U8, &[1], &config_data)
+        .expect("Failed to set input");
+    context.compute().expect("Failed to compute");
+    let output_bytes = get_data_from_context(&context, 0);
+    let spec = hound::WavSpec {
+        channels: 1,
+        sample_rate: 24000,
+        bits_per_sample: 32,
+        sample_format: hound::SampleFormat::Float,
+    };
+    let mut writer = hound::WavWriter::create("output1.wav", spec).unwrap();
+    let samples: Vec<f32> = output_bytes
+        .chunks_exact(4)
+        .map(|b| f32::from_le_bytes([b[0], b[1], b[2], b[3]]))
+        .collect();
+    for sample in samples {
+        writer.write_sample(sample).unwrap();
+    }
+    writer.finalize().unwrap();
+    graph.unload().expect("Failed to free resource");
+}