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

@ -1,59 +1,61 @@
package schema
import (
gopsutil "github.com/shirou/gopsutil/v3/process"
)
type BackendMonitorRequest struct {
Model string `json:"model" yaml:"model"`
}
type BackendMonitorResponse struct {
MemoryInfo *gopsutil.MemoryInfoStat
MemoryPercent float32
CPUPercent float64
}
type TTSRequest struct {
Model string `json:"model" yaml:"model"`
Input string `json:"input" yaml:"input"`
Voice string `json:"voice" yaml:"voice"`
Backend string `json:"backend" yaml:"backend"`
}
type StoresSet struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
}
type StoresDelete struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys"`
}
type StoresGet struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys" yaml:"keys"`
}
type StoresGetResponse struct {
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
}
type StoresFind struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Key []float32 `json:"key" yaml:"key"`
Topk int `json:"topk" yaml:"topk"`
}
type StoresFindResponse struct {
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
Similarities []float32 `json:"similarities" yaml:"similarities"`
}
package schema
import (
gopsutil "github.com/shirou/gopsutil/v3/process"
)
type BackendMonitorRequest struct {
Model string `json:"model" yaml:"model"`
}
type BackendMonitorResponse struct {
MemoryInfo *gopsutil.MemoryInfoStat
MemoryPercent float32
CPUPercent float64
}
// @Description TTS request body
type TTSRequest struct {
Model string `json:"model" yaml:"model"` // model name or full path
Input string `json:"input" yaml:"input"` // text input
Voice string `json:"voice" yaml:"voice"` // voice audio file or speaker id
Backend string `json:"backend" yaml:"backend"`
Language string `json:"language,omitempty" yaml:"language,omitempty"` // (optional) language to use with TTS model
}
type StoresSet struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
}
type StoresDelete struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys"`
}
type StoresGet struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Keys [][]float32 `json:"keys" yaml:"keys"`
}
type StoresGetResponse struct {
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
}
type StoresFind struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`
Key []float32 `json:"key" yaml:"key"`
Topk int `json:"topk" yaml:"topk"`
}
type StoresFindResponse struct {
Keys [][]float32 `json:"keys" yaml:"keys"`
Values []string `json:"values" yaml:"values"`
Similarities []float32 `json:"similarities" yaml:"similarities"`
}