This is an Ascend NPU adapted version of ResembleAI/chatterbox (Chatterbox TTS Multilingual). Adapted for single-card Ascend 910B (npu:0) with torch_npu.
Chatterbox is a 0.5B Llama backbone TTS with S3Gen (HiFiGAN) vocoder, VoiceEncoder and S3Tokenizer. It supports zero-shot voice cloning with emotion exaggeration control. This adaptation runs end-to-end text→waveform on Ascend NPU (T3 on NPU at ~36 it/s, S3Gen with istft CPU fallback for NPU UnfoldGrad bug).
npu:0 via ChatterboxTTS.from_local(model_dir, device="npu:0"); npu:0 verified with torch.npu.is_available(), torch.npu.get_device_name(0)=Ascend910_9362, param device npu:0, conds speaker_emb/prompt_token/prompt_feat on npu:0, output waveform device logged.perth stub (watermark bypass, not needed for core TTS)onnx stub (s3tokenizer import)transformers dep table patched (tokenizers>=0.20,<0.23, huggingface-hub<2.0)antlr4-python3-runtime==4.9.3 for omegaconfconds.pt load patched weights_only=False with map_location fix for NPUhifigan._istft patched with .contiguous() and CPU fallback on aclnnUnfoldGrad NPU error (sync fallback preserves waveform)text (default "Hello, this is a test of Chatterbox text to speech on Ascend NPU.", 65 chars) + builtin conds.pt (6s ENC / 10s DEC, S3_SR/S3GEN_SR), exaggeration=0.5, cfg_weight=0.5, temperature=0.8, seed=42pip install -r requirements.txt
python inference.py --device npu:0 --text "Hello, this is a test." --output output.wav
# or CPU:
python inference.py --device cpu --output output.wavSee inference.py for device proofs, synchronized timing (torch.npu.synchronize()), and validation (finite, RMS, clipping).
npu:0 vs 2.5 it/s on CPU (14× speedup), first compile + stable runs reportedwaveform_mae 0.0847, waveform_cosine -0.0017 (generative variance)spectral_convergence (512/1024/2048) 0.96-0.97, log_spectral_mae 0.27/0.33/0.42 with thresholds max 2.0 → PASS--max-spectral-convergence 2.0 --max-log-spectral-mae 2.0 --min-waveform-cosine -1.0t3 device npu:0, s3gen npu:0, ve npu:0, conds npu:0, input tokens npu:0, output npu:0 (watermarked wav on cpu after decode)torch.istft UnfoldGrad NPU op requires CPU fallback (async error logged, sync fallback succeeds). Pure NPU istft not yet supported on CANN 8.5.1.t3_mtl23ls_v3.safetensors) not exercised in this validation.

MIT (same as base). Watermark bypass stub is MIT-compatible.
Base model by Resemble AI. NPU adaptation via vLLM-Ascend / torch_npu.