model : add LiquidAI/LFM3-Audio-2B and LiquidAI/LFM3-Omni-2B (#31257)
* model : add LiquidAI/LFM3-Audio-2B and LiquidAI/LFM3-Omni-2B Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Assisted-by: Claude Opus 5.5 * convert : read the LFM3-Audio config.json as released A transformers that knows lfm3_audio rewrites the config into another layout (no lfm/encoder keys). Assisted-by: Claude Opus 5.5 * mtmd : disable flash attention for the LFM3-Audio depthformer Assisted-by: Claude Opus 5.5 * tts : add a voice option for LFM3-Audio and LFM3-Omni The model card offers a female and a male voice; --tts-voice for llama-tts, "voice" for the server /tts. Assisted-by: Claude Opus 5.5 * clean up template handling * convert : detect LFM3-Audio and LFM3-Omni by model_type Assisted-by: Claude Opus 5.5 * move banned tokens --> logits bias --> mtmd_helper * leave mtmd-cli unchanged * no more template_asr_system * left over * llama : keep the LFM3-Audio encoder convs and codec unquantized Assisted-by: Claude Opus 5.5 * common, mtmd : shorten comments Assisted-by: Claude Opus 5.5 --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
1 parent
eb7818c0b8
commit
19ff817fb2
31 files changed
+2727
-166
No files matched your search
@@ -120,7 +120,8 @@ struct mtmd_cli_context {
|
||||
init_vision_context(params);
|
||||
|
||||
mtmd_cap = mtmd_helper_get_capabilities(model, ctx_vision.get());
|
||||
if (!mtmd_cap.chat) {
|
||||
// a realtime transcription model has no chat, it streams the audio below
|
||||
if (!mtmd_cap.chat && !mtmd_cap.audio_stream) {
|
||||
LOG_ERR("Model does not support chat mode\n");
|
||||
LOG_ERR("Hint: for TTS models, please use llama-tts\n");
|
||||
exit(1);
|
||||
@@ -567,7 +568,10 @@ int main(int argc, char ** argv) {
|
||||
|
||||
if (g_is_interrupted) return 130;
|
||||
|
||||
if (ctx.mtmd_cap.audio_stream) {
|
||||
// realtime transcription models (no chat) transcribe while they listen, the others answer after the audio
|
||||
const bool transcribes = ctx.mtmd_cap.audio_stream && !ctx.mtmd_cap.chat;
|
||||
|
||||
if (transcribes) {
|
||||
if (params.image.size() != 1) {
|
||||
LOG_ERR("This model transcribes audio in realtime, pass exactly one --audio file\n");
|
||||
return 1;
|
||||
|
||||
Reference in new issue
Block a user