TTS API improvements (#2308)

* update doc on COQUI_LANGUAGE env variable

Signed-off-by: blob42 <contact@blob42.xyz>

* return errors from tts gRPC backend

Signed-off-by: blob42 <contact@blob42.xyz>

* handle speaker_id and language in coqui TTS backend

Signed-off-by: blob42 <contact@blob42.xyz>

* TTS endpoint: add optional language paramter

Signed-off-by: blob42 <contact@blob42.xyz>

* tts fix: empty language string breaks non-multilingual models

Signed-off-by: blob42 <contact@blob42.xyz>

* allow tts param definition in config file

- consolidate TTS options under `tts` config entry

Signed-off-by: blob42 <contact@blob42.xyz>

* tts: update doc

Signed-off-by: blob42 <contact@blob42.xyz>

---------

Signed-off-by: blob42 <contact@blob42.xyz>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Chakib Benziane 2024-06-01 20:26:27 +02:00 committed by GitHub
parent 95c65d67f5
commit b99182c8d4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 166 additions and 78 deletions

View file

@ -20,6 +20,7 @@ type TTSCMD struct {
Backend string `short:"b" default:"piper" help:"Backend to run the TTS model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Voice string `short:"v" help:"Voice name to run the TTS"`
Language string `short:"l" help:"Language to use with the TTS"`
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
@ -52,7 +53,7 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {
options := config.BackendConfig{}
options.SetDefaults()
filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, ml, opts, options)
filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
if err != nil {
return err
}