Neu-TTS-Nano-Q4-GGUF - Text-to-Speech Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python 3.10
• Picovoice Console Account

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/text-to-speech-benchmark.git

2. Install the dependencies:

pip3 install -r requirements/requirements-neu-tts-nano.txt

3. Download the picoLLM model

For each benchmark a picoLLM model is required to generate responses from the LLM. The picoLLM model used in the benchmark is llama-3.2-1b-instruct-385 and can be downloaded from Picovoice Console.

4. Run the benchmark:

Hugging face model download commit hash:

• Repo: neuphonic/neutts-nano-q4-gguf.
  • Commit hash: 8ae1694877fdf9d7c4a7bee2cc9775ba7eab3923.
• Repo: neuphonic/neucodec-onnx-decoder.
  • Commit hash: 55b95ccfb0b0a63bd033f0f78e6366607a616a33.

For core hour ratio & latency metrics:

python3 benchmark.py \
--picovoice-access-key ${PV_ACCESS_KEY} \
--picollm-model-path ${PICOLLM_MODEL_PATH} \
--engine neu_tts_nano_q4_gguf \
--neutts-ref-text-path ${REF_TEXT_PATH} \
--neutts-ref-codes-path ${REF_CODES_PATH} \

For peak memory metric:

for i in 1 2 3 4 5 6 7 8 9 10 20 40 80; do
    python3 benchmark.py \
    --picovoice-access-key ${PV_ACCESS_KEY} \
    --picollm-model-path ${PICOLLM_MODEL_PATH} \
    --engine neu_tts_nano_q4_gguf \
    --neutts-ref-text-path ${REF_TEXT_PATH} \
    --neutts-ref-codes-path ${REF_CODES_PATH} \
    --test-memory-size-multiple $i \
done

Replace ${REF_TEXT_PATH} with the path to the reference text for voice cloning. E.g. --neutts-ref-text-path ~/neutts/samples/jo.txt. Replace ${REF_CODES_PATH} with the path to the reference codes for voice cloning. E.g. --neutts-ref-codes-path ~/neutts/samples/jo.pt. Replace ${PICOLLM_MODEL_PATH} with the path to the model you downloaded. Replace ${PV_ACCESS_KEY} with your AccessKey obtained from Picovoice Console. Everyone who signs up for Picovoice Console receives a unique AccessKey.