Reduced binary size, updated model card
Browse files
README.md
CHANGED
|
@@ -60,11 +60,6 @@ runners
|
|
| 60 |
β βββ lfm2-audio-ubuntu-arm64.zip
|
| 61 |
βββ ubuntu-x64
|
| 62 |
βββ lfm2-audio-ubuntu-x64.zip
|
| 63 |
-
βΒ Β βββ llama-mtmd-cli
|
| 64 |
-
βββ ubuntu-x64
|
| 65 |
-
βββ bin
|
| 66 |
-
βββ llama-lfm2-audio
|
| 67 |
-
βββ llama-mtmd-cli
|
| 68 |
```
|
| 69 |
|
| 70 |
Each package contains `llama-lfm2-audio` and `llama-mtmd-cli` binaries.
|
|
@@ -83,14 +78,14 @@ The mode is defined by system prompt. There are limitations on system prompt and
|
|
| 83 |
ASR requires `-sys "Perform ASR."` and `--audio audio.wav` for input. It will print text to console
|
| 84 |
|
| 85 |
```console
|
| 86 |
-
|
| 87 |
```
|
| 88 |
|
| 89 |
### TTS
|
| 90 |
|
| 91 |
TTS requires `-sys "Perform TTS."`, `-p "What is this obsession people have with books?"` for input, and `--output output.wav` for output. It will save audio to `output.wav`.
|
| 92 |
```console
|
| 93 |
-
|
| 94 |
```
|
| 95 |
|
| 96 |
### Interleaved
|
|
@@ -98,7 +93,7 @@ bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-au
|
|
| 98 |
Interleaved produces both, text and audio as output, and can consume text or audio as input.
|
| 99 |
|
| 100 |
```console
|
| 101 |
-
|
| 102 |
```
|
| 103 |
|
| 104 |
## Run ASR using `llama-mtmd-cli`
|
|
@@ -106,7 +101,7 @@ bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-au
|
|
| 106 |
Build `llama-mtmd-cli` following the standard build procedure.
|
| 107 |
|
| 108 |
```console
|
| 109 |
-
|
| 110 |
```
|
| 111 |
|
| 112 |
### Debug
|
|
|
|
| 60 |
β βββ lfm2-audio-ubuntu-arm64.zip
|
| 61 |
βββ ubuntu-x64
|
| 62 |
βββ lfm2-audio-ubuntu-x64.zip
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
```
|
| 64 |
|
| 65 |
Each package contains `llama-lfm2-audio` and `llama-mtmd-cli` binaries.
|
|
|
|
| 78 |
ASR requires `-sys "Perform ASR."` and `--audio audio.wav` for input. It will print text to console
|
| 79 |
|
| 80 |
```console
|
| 81 |
+
lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform ASR." --audio $INPUT_WAV
|
| 82 |
```
|
| 83 |
|
| 84 |
### TTS
|
| 85 |
|
| 86 |
TTS requires `-sys "Perform TTS."`, `-p "What is this obsession people have with books?"` for input, and `--output output.wav` for output. It will save audio to `output.wav`.
|
| 87 |
```console
|
| 88 |
+
lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform TTS." -p "What is this obsession people have with books?" --output $OUTPUT_WAV
|
| 89 |
```
|
| 90 |
|
| 91 |
### Interleaved
|
|
|
|
| 93 |
Interleaved produces both, text and audio as output, and can consume text or audio as input.
|
| 94 |
|
| 95 |
```console
|
| 96 |
+
lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Respond with interleaved text and audio." --audio $INPUT_WAV --output $OUTPUT_WAV
|
| 97 |
```
|
| 98 |
|
| 99 |
## Run ASR using `llama-mtmd-cli`
|
|
|
|
| 101 |
Build `llama-mtmd-cli` following the standard build procedure.
|
| 102 |
|
| 103 |
```console
|
| 104 |
+
lfm2-audio-<platform>/llama-mtmd-cli -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -p "<__media__>" -sys "Perform ASR." --audio $INPUT_WAV
|
| 105 |
```
|
| 106 |
|
| 107 |
### Debug
|
runners/android-arm64/lfm2-audio-android-arm64.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf22f0ea2598adf9e686720d33a7ad180368b272e297d1186e72d545a547c80
|
| 3 |
+
size 4159454
|
runners/macos-arm64/lfm2-audio-macos-arm64.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cd724550d2518c33d5a0bf6c452da921299a0420f07ede80fb06695d541786b
|
| 3 |
+
size 3462697
|
runners/ubuntu-arm64/lfm2-audio-ubuntu-arm64.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53a14a2b2c4fc480f202100dda9fdf8268f88b8e655dbf688396ca3e4fdea925
|
| 3 |
+
size 5232143
|
runners/ubuntu-x64/lfm2-audio-ubuntu-x64.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f76116e2a4010de10fc5a61a0da5f77020a465478e18ac7fcdabde8e47ebe05
|
| 3 |
+
size 6282015
|