Model bark-small:fp16 already exists - Error loading GGUF models

[ekolawole]

Issue Description

emmanuelkolawole@EmmanueacStudio ~ % nexaai run /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf
API request failed: 400 Client Error: Bad Request for url: https://model-hub-backend.nexa4ai.com/model/download-tag-folder
Failed to get download models: 400 Client Error: Bad Request for url: https://model-hub-backend.nexa4ai.com/model/download-tag-folder
Failed to pull model /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf. If you are using local path, be sure to add --local_path and --model_type flags.
Unknown task: None. Skipping inference.
emmanuelkolawole@EmmanueacStudio ~ % nexaai run --local_path /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf --model_type AUDIO
Error: For Audio models with --local_path, the provided path must be a directory containing all related files.
emmanuelkolawole@EmmanueacStudio ~ % nexaai run bark-small:fp16
Model bark-small:fp16 already exists at /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf
Error running ggml inference: TTS model is not supported in CLI mode.
Please refer to our docs to install nexaai package: https://docs.nexaai.com/getting-started/installation
emmanuelkolawole@EmmanueacStudio ~ % nexaai run bark-small:fp16 -st
Model bark-small:fp16 already exists at /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf
Error running ggml inference: TTS model is not supported in CLI mode.
Please refer to our docs to install nexaai package: https://docs.nexaai.com/getting-started/installation
emmanuelkolawole@EmmanueacStudio ~ % nexa run bark-small:fp16 -st
Model bark-small:fp16 already exists at /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf
Unknown task: TTS. Skipping inference.

Steps to Reproduce

CMAKE_ARGS="-DGGML_METAL=ON -DSD_METAL=ON" pip install nexaai --prefer-binary --index-url https://nexaai.github.io/nexa-sdk/whl/metal --extra-index-url https://pypi.org/simple --no-cache-dir

Then run:
nexa run bark-small:fp16

emmanuelkolawole@EmmanueacStudio ~ % nexa run bark-small:fp16
Model bark-small:fp16 already exists at /Users/emmanuelkolawole/.cache/nexa/hub/official/bark-small/fp16.gguf
Error loading GGUF models, please refer to our docs to install nexaai package: https://docs.nexaai.com/getting-started/installation

OS

Sonoma 14.5

Python Version

3.11

Nexa SDK Version

0.0.9.5

GPU (if using one)

No response

[unseenmars]

bark_cpp is temporarily disabled since version v0.0.9.3. We will provide more updates on this very soon.