Instructions to use 47z/glm-4-voice-decoder-emo-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KimiAudio
How to use 47z/glm-4-voice-decoder-emo-ft with KimiAudio:
# Example usage for KimiAudio # pip install git+https://github.com/MoonshotAI/Kimi-Audio.git "transformers<5" import soundfile as sf from kimia_infer.api.kimia import KimiAudio model = KimiAudio(model_path="47z/glm-4-voice-decoder-emo-ft", load_detokenizer=True) sampling_params = { "audio_temperature": 0.8, "audio_top_k": 10, "text_temperature": 0.0, "text_top_k": 5, } # For ASR asr_audio = "asr_example.wav" messages_asr = [ {"role": "user", "message_type": "text", "content": "Please transcribe the following audio:"}, {"role": "user", "message_type": "audio", "content": asr_audio} ] _, text = model.generate(messages_asr, **sampling_params, output_type="text") print(text) # For Q&A qa_audio = "qa_example.wav" messages_conv = [{"role": "user", "message_type": "audio", "content": qa_audio}] wav, text = model.generate(messages_conv, **sampling_params, output_type="both") sf.write("output_audio.wav", wav.cpu().view(-1).numpy(), 24000) print(text) - Notebooks
- Google Colab
- Kaggle
Download epoch500_emoft.pt from 47z/glm-4-voice-decoder-emo-ft: direct link, hf CLI and curl.
- Browser
- Download file 445 MB
-
https://huggingface.co/47z/glm-4-voice-decoder-emo-ft/resolve/main/epoch500_emoft.pt
- Command line
-
hf download hf://47z/glm-4-voice-decoder-emo-ft/epoch500_emoft.pt
-
curl -L -o epoch500_emoft.pt https://huggingface.co/47z/glm-4-voice-decoder-emo-ft/resolve/main/epoch500_emoft.pt
445 MB
- Xet hash:
- 82c6acea78e247c78eca3f33615b18abf1b7592190c38d96616af3333a31add1
- Size of remote file:
- 445 MB
- SHA256:
- 3046ec9c962a0e7bf6992a4678d0d3cd1605c1a829a6ae167d547b44137f698c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.