cmeraki commited on
Commit
d54ff5b
1 Parent(s): c1e068f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -53,7 +53,7 @@ It models audio as tokens and can generate high-quality audio with consistent st
53
 
54
  1. Extremely small, based on GPT-2 small architecture. The methodology can be extended to any autoregressive transformer-based architecture.
55
  2. Ultra-fast. Using our [self hosted service option](#self-hosted-service), on RTX6000Ada NVIDIA GPU the model can achieve speeds up to 400 toks/s (4s of audio generation per s) and under 20ms time to first token.
56
- 3. On RTX6000Ada, it can support a batch size of 1k with full context length of 1024 tokens
57
  4. Supports voice cloning with small prompts (<5s).
58
  5. Code mixing text input in 2 languages - English and Hindi.
59
 
@@ -62,7 +62,7 @@ It models audio as tokens and can generate high-quality audio with consistent st
62
  1. Model Type: GPT-2 based language model
63
  2. Size: 124M parameters
64
  3. Language Support: English, Hindi
65
- 4. License: This model is not for commercial use. This is only a research showcase.
66
 
67
  ## Technical details
68
 
 
53
 
54
  1. Extremely small, based on GPT-2 small architecture. The methodology can be extended to any autoregressive transformer-based architecture.
55
  2. Ultra-fast. Using our [self hosted service option](#self-hosted-service), on RTX6000Ada NVIDIA GPU the model can achieve speeds up to 400 toks/s (4s of audio generation per s) and under 20ms time to first token.
56
+ 3. On RTX6000Ada, it can support a batch size of ~1000 sequences with full context length of 1024 tokens
57
  4. Supports voice cloning with small prompts (<5s).
58
  5. Code mixing text input in 2 languages - English and Hindi.
59
 
 
62
  1. Model Type: GPT-2 based language model
63
  2. Size: 124M parameters
64
  3. Language Support: English, Hindi
65
+ 4. License: This model is not for commercial usage. This is only a research showcase.
66
 
67
  ## Technical details
68